© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7432
    Prev
    Next
    INDEX
    Explanations

    terms related to acceptance and support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    кульп
    -0.50
     Got
    -0.49
     refuse
    -0.46
     love
    -0.45
     respect
    -0.44
     stole
    -0.44
     trust
    -0.43
     sunk
    -0.42
     got
    -0.42
     surfaced
    -0.42
    POSITIVE LOGITS
     favored
    1.65
     favoured
    1.63
     adored
    1.45
     preferred
    1.41
    Loved
    1.36
     appreciated
    1.35
     loved
    1.35
     accepted
    1.34
    accepted
    1.30
    preferred
    1.30
    Activations Density 0.293%

    No Known Activations