© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 40034
    Prev
    Next
    INDEX
    Explanations

    references to being grounded and concepts related to stability or safety

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

    ground level

    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
    Bảo
    -0.40
    multirow
    -0.36
    ))-
    -0.35
    jsdelivr
    -0.35
     HttpNotFound
    -0.33
     Fauci
    -0.31
    endpush
    -0.30
    NoSuchAlgorithm
    -0.29
     Med
    -0.28
    atorias
    -0.28
    POSITIVE LOGITS
     ground
    2.27
    ground
    1.94
     Ground
    1.92
    Ground
    1.91
     GROUND
    1.88
    GROUND
    1.73
    地面
    1.56
     grounded
    1.53
     grounding
    1.40
    grounded
    1.38
    Activations Density 0.113%

    No Known Activations