© 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. 6157
    Prev
    Next
    INDEX
    Explanations

    technical and procedural terms related to software and its usage conditions

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

    Text before periods

    np_acts-logits-general · gemini-2.0-flash

    feedback, article, torque, air, selections, short

    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
     of
    -2.82
     của
    -1.53
    ของ
    -1.51
    of
    -1.34
     της
    -1.09
     של
    -1.05
     ของ
    -0.96
     των
    -0.96
     Of
    -0.94
    Of
    -0.91
    POSITIVE LOGITS
    RenderAtEndOf
    1.07
    windowFixed
    1.00
    +#+#
    0.93
    webElementGuid
    0.92
    ⓧ
    0.91
     للاسماء
    0.88
    #
    0.84
    Autoritní
    0.82
    évaluateur
    0.81
    Tikang
    0.81
    Activations Density 0.753%

    No Known Activations