© 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. 104663
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating degrees or comparisons

    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
     karş
    -0.38
    whatever
    -0.32
     invitaciones
    -0.32
     gobier
    -0.31
     campur
    -0.31
     whatever
    -0.30
     convocatoria
    -0.30
     relatos
    -0.29
    something
    -0.29
     procédures
    -0.29
    POSITIVE LOGITS
    expandindo
    0.97
    enumii
    0.93
     незавершена
    0.91
     BoxDecoration
    0.90
    RenderAtEndOf
    0.89
    OGND
    0.88
    ValueStyle
    0.87
    脚注の使い方
    0.85
    تقاوى
    0.85
    Geplaatst
    0.85
    Activations Density 0.121%

    No Known Activations