© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6654
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation that indicate specific formatting or structure in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    こ
    -0.45
     спро
    -0.41
    creep
    -0.41
    ailles
    -0.40
     creep
    -0.40
    owanego
    -0.39
     pretend
    -0.39
     Internet
    -0.39
    روش
    -0.39
     đời
    -0.38
    POSITIVE LOGITS
     للمعارف
    0.89
     resourceCulture
    0.84
     يتيمه
    0.76
    ⓧ
    0.75
    Демографія
    0.74
    djangoproject
    0.72
    ագրություններ
    0.70
     continúas
    0.68
    Tembelea
    0.68
    RuleContext
    0.67
    Activations Density 0.240%

    No Known Activations