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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 3147
    Prev
    Next
    INDEX
    Explanations

    references to meetings and hearings

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

    formal gatherings

    np_acts-logits-general · gemini-2.0-flash

    meetings and hearings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.67
     BrowserModule
    -0.62
    }))
    
    -0.60
    MigrationBuilder
    -0.58
     BoxFit
    -0.56
    AnimationsModule
    -0.56
    )++;
    -0.53
     препратки
    -0.53
    Награды
    -0.51
    ]<<"
    -0.50
    POSITIVE LOGITS
     held
    1.03
     attended
    1.00
     hosted
    0.95
     conducted
    0.92
     convened
    0.90
     diadakan
    0.86
     Held
    0.83
    held
    0.81
    Held
    0.81
     gehouden
    0.79
    Activations Density 0.360%

    No Known Activations