© 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
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 4720
    Prev
    Next
    INDEX
    Explanations

    references to concealment or secrecy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.43
    Empereur
    -0.41
     uyar
    -0.37
    TableAdapter
    -0.36
    équipement
    -0.35
    MessageOf
    -0.33
     bomberos
    -0.33
    AudioManager
    -0.32
    Смотрите
    -0.32
    がき
    -0.32
    POSITIVE LOGITS
     hidden
    3.03
     concealed
    2.75
     hiding
    2.69
     Hidden
    2.63
    Hidden
    2.55
     hid
    2.42
    hidden
    2.42
     hides
    2.36
     hide
    2.36
     conceal
    2.33
    Activations Density 0.361%

    No Known Activations