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. 1-GEMMASCOPE-RES-16K
    6. 6931
    Prev
    Next
    INDEX
    Explanations

    coding tasks related to file manipulation in a build process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.98
    Personensuche
    -0.88
    GEBURTS
    -0.80
    RTLD
    -0.76
     myſelf
    -0.75
     purpoſe
    -0.74
     itſelf
    -0.71
     pleaſure
    -0.71
     juſ
    -0.71
    TypedDataSet
    -0.69
    POSITIVE LOGITS
    P
    0.42
     agregó
    0.41
    (
    0.41
    pola
    0.37
    remove
    0.36
     Separate
    0.36
     +=
    0.36
        
    0.36
    foot
    0.36
     rispet
    0.35
    Activations Density 1.379%

    No Known Activations