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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 23-GEMMASCOPE-RES-131K
    6. 23195
    Prev
    Next
    INDEX
    Explanations

    variable declarations in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InSection
    -0.40
     nødvendig
    -0.39
    Automatically
    -0.38
    兜
    -0.38
     prohibido
    -0.38
    Vendo
    -0.37
     spørgsmål
    -0.36
    conce
    -0.35
     nød
    -0.35
     unteren
    -0.35
    POSITIVE LOGITS
    RTLR
    0.60
     ProtoMessage
    0.56
     lateinit
    0.50
    
    0.50
     TestBed
    0.46
    ChildScrollView
    0.46
     
    0.46
    ']>;
    0.46
    
    0.44
    Cyfeiriadau
    0.43
    Activations Density 0.001%

    No Known Activations