© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 684
    Prev
    Next
    INDEX
    Explanations

    phrases questioning the validity of assumptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases expressing nuanced logical reasoning, particularly those using "does not mean" or similar qualifying language that suggests a subtle distinction or caveat.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    AndEndTag
    -0.89
    AddTagHelper
    -0.70
     للاسماء
    -0.64
    RenderAtEndOf
    -0.61
    expandindo
    -0.60
     فريبيس
    -0.59
    󠁣
    -0.59
    IntoConstraints
    -0.56
    يكب
    -0.54
    
    -0.54
    POSITIVE LOGITS
     تضيفلها
    0.38
     trotzdem
    0.38
    toggler
    0.37
    Federal
    0.35
    不一定
    0.34
     construction
    0.33
     fer
    0.33
     Federal
    0.32
     Construction
    0.31
     buoni
    0.31
    Activations Density 0.221%

    No Known Activations