© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8063
    Prev
    Next
    INDEX
    Explanations

    intensifiers that emphasize extreme qualities or degrees of attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    もはや
    -0.68
     depoz
    -0.67
    Smaller
    -0.65
     davantage
    -0.65
     Mejor
    -0.64
     Menace
    -0.64
    ReusableCell
    -0.63
     almeno
    -0.63
    Przypisy
    -0.62
    Larger
    -0.61
    POSITIVE LOGITS
     extremely
    1.10
     very
    1.06
     incredibly
    1.00
    extremely
    0.96
     extraordinarily
    0.93
     Extremely
    0.88
    Extremely
    0.85
    非常
    0.84
    very
    0.84
     VERY
    0.84
    Activations Density 0.307%

    No Known Activations