Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 74681
    Prev
    Next
    INDEX
    Explanations

    instances of whitespace or line breaks in the document

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

    alias, CALL, #, tz, sscanf, user

    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
    Бахар
    -0.60
    LEncoder
    -0.60
     intptr
    -0.59
    StoryboardSegue
    -0.59
     كومونز
    -0.56
    pertory
    -0.55
    bootstrapcdn
    -0.55
    msgSender
    -0.55
     Exacts
    -0.54
     BoxFit
    -0.54
    POSITIVE LOGITS
     pleaſure
    0.39
     Wikiseite
    0.36
    selben
    0.36
    AlreadyExists
    0.35
     fometimes
    0.34
    Referencie
    0.34
    Törté
    0.34
     fubject
    0.33
     purpoſe
    0.33
    GenerationType
    0.33
    Activations Density 0.007%

    No Known Activations