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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-GEMMASCOPE-RES-16K
    6. 2267
    Prev
    Next
    INDEX
    Explanations

    instances of prominent actions or performances in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vivant
    -0.49
    hod
    -0.47
     avancé
    -0.47
     cost
    -0.47
    cost
    -0.47
    lol
    -0.46
    Rule
    -0.45
    mobileqq
    -0.44
    fors
    -0.44
     lol
    -0.43
    POSITIVE LOGITS
    脚注の使い方
    0.93
     AssemblyCulture
    0.87
    httphttps
    0.85
     Мексичка
    0.84
    دانشنامهٔ
    0.84
     chi̍t
    0.84
    prepareStatement
    0.78
    IntoConstraints
    0.77
    MemoryWarning
    0.77
     GenerationType
    0.71
    Activations Density 0.127%

    No Known Activations