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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 9056
    Prev
    Next
    INDEX
    Explanations

    terms related to evidence or demonstration of truth and credibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Chandigarh
    -0.56
    llac
    -0.56
    multer
    -0.54
    ributors
    -0.54
    Midnight
    -0.53
    getChildren
    -0.53
    rogels
    -0.52
    finement
    -0.52
    schild
    -0.52
    IKit
    -0.52
    POSITIVE LOGITS
     Prove
    1.35
     prove
    1.34
     proving
    1.29
     proved
    1.27
    Prove
    1.24
     proves
    1.23
     Proving
    1.19
    prove
    1.13
     proof
    1.09
     proven
    1.08
    Activations Density 0.276%

    No Known Activations