© 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. 4411
    Prev
    Next
    INDEX
    Explanations

    terms related to applications and implementations in various contexts

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

    mainly/mostly/primarily introducing focus

    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
    DockStyle
    -0.56
    adaptiveStyles
    -0.54
    mschrijving
    -0.50
    poptosis
    -0.50
     begge
    -0.49
     MutableLiveData
    -0.48
    estacks
    -0.48
    numerusform
    -0.48
     itſelf
    -0.47
    alakip
    -0.47
    POSITIVE LOGITS
     mainly
    0.80
     Mainly
    0.77
     mostly
    0.77
    Mostly
    0.76
     Mostly
    0.75
     primarily
    0.75
    mainly
    0.73
    Mainly
    0.73
    mostly
    0.73
     Primarily
    0.66
    Activations Density 0.064%

    No Known Activations