© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 83054
    Prev
    Next
    INDEX
    Explanations

    terms related to pipeline inspection and safety issues

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

    pipeline inspector, corrosion, oversight

    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
     SwitchCompat
    -0.49
     дописавши
    -0.43
    verifyException
    -0.41
     nahilalakip
    -0.41
    archiviato
    -0.41
    хьтан
    -0.39
     experimented
    -0.39
     مشين
    -0.38
    anneer
    -0.38
     AssemblyVersion
    -0.36
    POSITIVE LOGITS
    MessageOf
    0.52
    ⓧ
    0.49
    RenderAtEndOf
    0.43
    BeginContext
    0.41
    andExpect
    0.40
    majánló
    0.38
     validamos
    0.35
     legale
    0.35
    QMetaType
    0.35
     valutazione
    0.34
    Activations Density 0.145%

    No Known Activations