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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 4838
    Prev
    Next
    INDEX
    Explanations

    words or phrases that convey a sense of disturbance or unsettling feelings

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

    disturbing content

    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
    GameMode
    -0.58
     pouvoit
    -0.56
    kannya
    -0.54
     îna
    -0.52
    GHIJKLM
    -0.51
     viață
    -0.51
    rungsseite
    -0.51
    ᅠ
    -0.51
    kháu
    -0.50
    RTEX
    -0.49
    POSITIVE LOGITS
     disturbing
    1.73
     disturbed
    1.50
     disturb
    1.48
    urbing
    1.45
     distur
    1.38
     disturbance
    1.25
     Disturb
    1.23
     disturbances
    1.09
    urbed
    1.05
     troubling
    0.92
    Activations Density 0.007%

    No Known Activations