© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 4918
    Prev
    Next
    INDEX
    Explanations

    references to art, science, and nature-related subjects

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

    before names of institutions

    np_acts-logits-general · gemini-2.0-flash

    concept followed by institution type

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    SequentialGroup
    -0.68
     Bewußt
    -0.63
     étoit
    -0.56
     Verhältnisse
    -0.54
    GraphicsUnit
    -0.53
    enumii
    -0.53
    ftagPool
    -0.53
     Kindheit
    -0.52
     réglable
    -0.50
    +#+#
    -0.49
    POSITIVE LOGITS
    postsleuth
    0.55
    цуз
    0.44
     envelope
    0.41
    OwnProperty
    0.41
     Accident
    0.40
     advisory
    0.39
     profi
    0.38
     CE
    0.38
     support
    0.38
     Psi
    0.37
    Activations Density 2.443%

    No Known Activations