© 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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105598
    Prev
    Next
    INDEX
    Explanations

    terms associated with technical specifications and medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AISSEE
    -0.50
    yntaxException
    -0.49
    BufferException
    -0.40
     sucede
    -0.39
     compromisso
    -0.38
     sucedió
    -0.38
     ويكي
    -0.37
     suceder
    -0.37
    ViewFeatures
    -0.36
     indruk
    -0.36
    POSITIVE LOGITS
    __*/
    0.67
     insur
    0.50
    ---*/
    0.48
    GenerationType
    0.46
    }-*/;
    0.46
     carni
    0.45
    skjaer
    0.42
    TypedDataSet
    0.42
     protoimpl
    0.41
    :✨
    0.41
    Activations Density 0.181%

    No Known Activations