© 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. 3076
    Prev
    Next
    INDEX
    Explanations

    references to social justice and advocacy-related themes

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

    "Impact Factory" or Utah-related content

    np_acts-logits-general · gemini-2.0-flash

    Impact Factory Utah

    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
    posedge
    -0.99
    ratulations
    -0.86
    modity
    -0.78
    prehensive
    -0.77
    ++)
    
    -0.73
    %;
    
    -0.72
    æa
    -0.72
    ']->
    -0.71
    erapeutic
    -0.71
    stacle
    -0.71
    POSITIVE LOGITS
     Shakspeare
    1.04
     itſelf
    1.01
     purpoſe
    0.94
     pleaſure
    0.93
     Majefty
    0.92
     ſame
    0.92
     ſche
    0.92
    ſelf
    0.92
     Jefus
    0.90
     Theſe
    0.89
    Activations Density 0.350%

    No Known Activations