© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 176
    Prev
    Next
    INDEX
    Explanations

    references to various actions or indicators of progress in a context

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

    head and decapitation vocabulary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     orgánico
    -0.44
     bonté
    -0.43
     Económica
    -0.43
     irmã
    -0.42
     WJ
    -0.42
     bize
    -0.41
     spreken
    -0.40
    WMS
    -0.40
    StateException
    -0.40
     roxo
    -0.40
    POSITIVE LOGITS
     đầu
    2.34
    ầu
    0.98
    ראש
    0.79
     HEAD
    0.73
    Head
    0.70
     Head
    0.69
     cuối
    0.67
    ̀u
    0.66
    rungsseite
    0.66
     awal
    0.64
    Activations Density 0.001%

    No Known Activations