© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 9944
    Prev
    Next
    INDEX
    Explanations

    various technical and contextual aspects related to radio broadcasts and data processes

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

    the word "where"

    np_acts-logits-general · gemini-2.0-flash

    where following a noun

    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
    XtraBars
    -0.43
     arşivlendi
    -0.42
    arschijnlijk
    -0.41
    soever
    -0.40
    SerializedName
    -0.38
    mentaux
    -0.38
    ysacchar
    -0.37
    ichier
    -0.36
    tilities
    -0.36
    $_['
    -0.35
    POSITIVE LOGITS
     where
    3.64
    where
    2.88
     donde
    2.75
     où
    2.52
     где
    2.44
     gdzie
    2.31
     Where
    2.28
    Where
    2.25
     hvor
    2.19
     wherein
    2.16
    Activations Density 2.670%

    No Known Activations