© 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. 30-GEMMASCOPE-RES-16K
    11. 15327
    Prev
    Next
    INDEX
    Explanations

    references to research, inquiry, and exploration of societal issues

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    abstract concepts and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     State
    -0.27
     kind
    -0.26
     Gods
    -0.25
     of
    -0.24
     .
    -0.24
     twice
    -0.24
    VYMaps
    -0.23
     nu
    -0.23
    PREFERRED
    -0.22
     Collections
    -0.22
    POSITIVE LOGITS
     utafitiHapana
    0.82
     toward
    0.67
     către
    0.65
    Autoritní
    0.65
    toward
    0.63
     towards
    0.62
    SequentialGroup
    0.62
    exitRule
    0.61
     autorytatywna
    0.61
     HttpNotFound
    0.61
    Activations Density 0.874%

    No Known Activations