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. 4-GEMMASCOPE-RES-16K
    6. 3392
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters, particularly asterisks and underscores used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.79
     Roskov
    -0.76
    WriteTagHelper
    -0.73
    IUrlHelper
    -0.71
     насељу
    -0.71
    UrlResolution
    -0.71
    MigrationBuilder
    -0.70
     lenker
    -0.68
     poveznice
    -0.68
    tvguidetime
    -0.68
    POSITIVE LOGITS
    <i>
    0.62
    <em>
    0.61
     literally
    0.57
     ogóle
    0.55
     really
    0.53
    <u>
    0.52
    textit
    0.49
     even
    0.49
     actually
    0.49
     simply
    0.48
    Activations Density 0.358%

    No Known Activations