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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 12662
    Prev
    Next
    INDEX
    Explanations

    references to South Africans and their cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.71
     HasFactory
    -0.63
     transfieras
    -0.62
    styleType
    -0.59
    xos
    -0.59
    Autoritní
    -0.55
    artifactId
    -0.52
    apist
    -0.51
    หวัด
    -0.51
    Reminds
    -0.50
    POSITIVE LOGITS
     arrivals
    0.56
     arriving
    0.56
     ExecuteAsync
    0.54
     arrived
    0.51
    Inflater
    0.49
     resourceCulture
    0.49
    AntiForgeryToken
    0.49
     presence
    0.48
    ViewFeatures
    0.48
    InSection
    0.47
    Activations Density 0.468%

    No Known Activations