© 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. 68504
    Prev
    Next
    INDEX
    Explanations

    multiple forms of quotation marks and their variations, indicating speech or emphasis

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

    content within quotes

    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
    UnsafeEnabled
    -0.51
     CreateTagHelper
    -0.43
     besluit
    -0.41
     parteci
    -0.39
    — 
    -0.39
     yourselves
    -0.38
     acrescent
    -0.38
    zędu
    -0.38
     espelho
    -0.37
     élevées
    -0.36
    POSITIVE LOGITS
     Waray
    0.47
     fake
    0.45
    GraphicsUnit
    0.44
    hoeddwyd
    0.42
    styleUrls
    0.42
     ويكيپيديا
    0.42
    LEn
    0.42
     allegedly
    0.41
    ViewImports
    0.41
    SetBool
    0.41
    Activations Density 0.092%

    No Known Activations