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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8652
    Prev
    Next
    INDEX
    Explanations

    syntactical structures associated with function and control flow in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.54
    клопе
    -0.54
    Bibliograf
    -0.53
    বহ
    -0.52
    CPtr
    -0.51
    FileDescriptor
    -0.50
    oneofs
    -0.50
    Hozzáférés
    -0.50
    loon
    -0.50
    fromnode
    -0.50
    POSITIVE LOGITS
     case
    1.06
    case
    0.86
     Case
    0.80
     cases
    0.80
     Cases
    0.79
     caso
    0.77
    default
    0.75
    Case
    0.75
     default
    0.74
    Default
    0.72
    Activations Density 0.077%

    No Known Activations