© 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. 17-GEMMASCOPE-RES-16K
    6. 9298
    Prev
    Next
    INDEX
    Explanations

    conjunctions and linking phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    舺
    -0.53
    ectoria
    -0.50
    awaiter
    -0.50
    テー
    -0.48
     @"/
    -0.48
    IVEREF
    -0.47
     jo
    -0.46
    dez
    -0.46
     Wiktionnaire
    -0.45
    Trail
    -0.45
    POSITIVE LOGITS
    glTexCoord
    0.67
     protoimpl
    0.65
     otomatig
    0.59
     sumpay
    0.59
    crose
    0.57
     DBNull
    0.55
    ^(@)
    0.55
    SizeMode
    0.54
     Crooked
    0.52
    breviation
    0.51
    Activations Density 0.340%

    No Known Activations