© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 118715
    Prev
    Next
    INDEX
    Explanations

    references to artifact IDs in dependency management settings

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

    artifactId, UA, lang

    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
    nodoc
    -0.54
    libft
    -0.48
    SequentialGroup
    -0.48
    Identyfik
    -0.41
    tagHelperRunner
    -0.39
    nestjs
    -0.39
     виправивши
    -0.37
    ępu
    -0.37
    rxjs
    -0.37
    setVerticalGroup
    -0.37
    POSITIVE LOGITS
    UA
    1.35
     UA
    1.13
     ua
    0.75
    ua
    0.61
    ंदीखरीदारी
    0.58
    Ua
    0.58
    UAS
    0.49
    tonode
    0.48
    RegistryLite
    0.46
    prete
    0.45
    Activations Density 0.001%

    No Known Activations