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. 9-GEMMASCOPE-RES-16K
    6. 15392
    Prev
    Next
    INDEX
    Explanations

    preprocessor directives and compilation commands in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useRef
    -0.56
    ViewHolder
    -0.56
    TALL
    -0.54
    alii
    -0.54
    IntoConstraints
    -0.53
     Follow
    -0.53
    																										
    -0.52
    zí
    -0.52
     AppCompat
    -0.52
    libft
    -0.52
    POSITIVE LOGITS
    ":[{
    0.95
    
    0.79
     AssemblyVersion
    0.77
     MenuView
    0.73
     <<<<<<<<<<<<<<
    0.73
     Cip
    0.73
     ModelExpression
    0.72
    منابع
    0.71
    الإنجليزية
    0.71
     devaient
    0.70
    Activations Density 0.051%

    No Known Activations