© 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. 64941
    Prev
    Next
    INDEX
    Explanations

    the presence of instructional language or mathematical operations

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

    mathematical expressions and code

    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
     Roskov
    -0.64
     <=",
    -0.59
     disambiguazione
    -0.54
     Chwiliwch
    -0.53
    DMETHOD
    -0.49
    RenderAtEndOf
    -0.49
    orsese
    -0.49
    Pozri
    -0.48
    észetes
    -0.48
     Boek
    -0.48
    POSITIVE LOGITS
    dersfield
    0.37
     ImageIcon
    0.35
    siger
    0.35
     StringIO
    0.34
    humans
    0.31
    addGap
    0.31
     aarde
    0.31
    Stderr
    0.31
    Human
    0.31
    XmlAttribute
    0.31
    Activations Density 0.253%

    No Known Activations