Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14653
    Prev
    Next
    INDEX
    Explanations

    elements related to user interactions and data processing in a software context

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

    Numbers inside brackets

    np_acts-logits-general · gemini-2.0-flash

    data match

    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
     desto
    -0.51
     ◄
    -0.51
    dete
    -0.48
     <<<<<<<<<<<<<<
    -0.47
     Cyrus
    -0.45
     getItemId
    -0.43
     Rosalind
    -0.43
     كومونز
    -0.42
     Bartholo
    -0.42
    ίος
    -0.42
    POSITIVE LOGITS
    <h4>
    1.37
    
    0.86
    <th>
    0.75
    InputBorder
    0.66
    ")->
    0.66
    SequentialGroup
    0.65
    <?
    0.65
     дописавши
    0.64
    </h4>
    0.64
    subsubsection
    0.61
    Activations Density 0.152%

    No Known Activations