© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7749
    Prev
    Next
    INDEX
    Explanations

    references to file manipulation and data processing in code

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

    Code, symbols, and equation fragments

    np_acts-logits-general · gemini-2.0-flash

    C/C++ field access

    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
    .,
    -0.49
     (
    -0.46
    .
    -0.45
    </em>
    -0.45
     da
    -0.45
    ,
    -0.45
    </h2>
    -0.44
     good
    -0.44
     
    -0.44
    ;
    -0.43
    POSITIVE LOGITS
     समीक्षाओं
    0.99
    Obrázky
    0.94
     GenerationType
    0.93
    MethodManager
    0.91
     purpoſe
    0.91
     Efq
    0.91
    AndEndTag
    0.89
     useAppContext
    0.88
     дописавши
    0.88
    ItemBackground
    0.86
    Activations Density 0.152%

    No Known Activations