© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10639
    Prev
    Next
    INDEX
    Explanations

    numeric values related to legal or financial contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    strings of characters that are part of a program, specifically looking for patterns related to splitting and manipulating data in a code context.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    proper nouns, particularly names of people, companies, and places.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Text after named entities or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    proper nouns and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -1.41
     مشين
    -1.39
    ContentAsync
    -1.38
    CloseOperation
    -1.30
    setVerticalGroup
    -1.30
    ChildScrollView
    -1.30
    RenderAtEndOf
    -1.24
     Monfieur
    -1.21
    DockStyle
    -1.21
    RectangleBorder
    -1.20
    POSITIVE LOGITS
     
    0.91
     de
    0.82
    ,
    0.81
     I
    0.79
     in
    0.79
    </em>
    0.78
     and
    0.77
    <eos>
    0.77
    .
    0.76
     por
    0.74
    Activations Density 0.743%

    No Known Activations