© 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. 38-GEMMASCOPE-RES-16K
    6. 9610
    Prev
    Next
    INDEX
    Explanations

    terms related to execution or decisive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.38
    URLException
    -0.37
    extAlignment
    -0.37
    ContentLoaded
    -0.36
    LookAnd
    -0.36
     CreateTagHelper
    -0.35
    onViewCreated
    -0.34
    astify
    -0.34
    NonNull
    -0.34
     kaynağından
    -0.33
    POSITIVE LOGITS
    ers
    2.67
    ERS
    1.97
    er
    1.67
    者
    1.27
    ER
    1.16
    ersk
    1.06
    erski
    1.04
    erst
    1.03
    ership
    0.95
    ersch
    0.93
    Activations Density 0.886%

    No Known Activations