© 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. 97481
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or significant instances of "the."

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

    even the

    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
    balleur
    -0.35
     nakalista
    -0.34
    姦
    -0.33
    บัติ
    -0.33
     presentarse
    -0.32
    nextProps
    -0.31
     ň
    -0.31
     tatuagem
    -0.31
     boneca
    -0.30
    chieht
    -0.30
    POSITIVE LOGITS
     kasarigan
    0.58
     HasFactory
    0.57
    providedIn
    0.56
    kusen
    0.52
    eders
    0.52
    ragamo
    0.51
    OrBuilder
    0.49
    fjspx
    0.49
    atial
    0.49
    emed
    0.48
    Activations Density 0.046%

    No Known Activations