© 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. 31-GEMMASCOPE-RES-131K
    6. 38411
    Prev
    Next
    INDEX
    Explanations

    negative impacts or adverse effects in various contexts

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

    adversely affected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVENESS
    -0.37
    XtraReports
    -0.34
    ul
    -0.30
    φό
    -0.30
    ोड
    -0.28
     NgModule
    -0.28
    észetes
    -0.27
    dom
    -0.27
    pemb
    -0.26
    TabIndex
    -0.26
    POSITIVE LOGITS
     affected
    2.44
     impacted
    2.41
     impact
    2.34
     impacts
    2.20
     Affected
    2.19
    impact
    2.13
    affected
    2.13
    Impact
    2.11
     Impact
    2.03
    Affected
    2.02
    Activations Density 0.302%

    No Known Activations