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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1290
    Prev
    Next
    INDEX
    Explanations

    phrases related to the consequences or effects of actions or events

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

    "Impact" followed by "of" or "Factory"

    np_acts-logits-general · gemini-2.0-flash

    Impact Factory or impact of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     généraux
    -0.82
     GenerationType
    -0.76
     authService
    -0.73
    Nye
    -0.72
    gameserver
    -0.71
    
    -0.70
    arz
    -0.69
     CURIAM
    -0.69
     TextAppearance
    -0.69
     supérieurs
    -0.68
    POSITIVE LOGITS
     impacts
    1.22
    Impacts
    1.20
     impact
    1.14
     Impacts
    1.12
     IMPACT
    1.06
     Impact
    1.04
     impacting
    1.01
     impacted
    0.98
    IMPACT
    0.96
    impact
    0.95
    Activations Density 0.081%

    No Known Activations