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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2594
    Prev
    Next
    INDEX
    Explanations

    expressions related to data manipulation and programming functions

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

    Code snippets and programming syntax

    np_acts-logits-general · gemini-2.0-flash

    code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -1.07
     postIndex
    -0.89
    principalColumn
    -0.89
     ProtoMessage
    -0.88
     NSCoder
    -0.84
    SequentialGroup
    -0.84
     estekak
    -0.82
     nakalista
    -0.82
     unknownFields
    -0.81
    CodedInputStream
    -0.80
    POSITIVE LOGITS
    ↵↵
    0.55
    ↵↵↵
    0.51
    ↵↵↵↵
    0.46
     présentes
    0.41
    else
    0.41
     now
    0.40
     súčas
    0.40
    now
    0.39
    ↵↵↵↵↵
    0.39
    ziná
    0.38
    Activations Density 0.057%

    No Known Activations