© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4298
    Prev
    Next
    INDEX
    Explanations

    sections or phrases that provide descriptive information about entities or topics

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

    "about"

    np_acts-logits-general · gemini-2.0-flash

    about harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GTCX
    -0.57
    addCriterion
    -0.52
    RTEE
    -0.52
    hisattva
    -0.52
    jwa
    -0.51
    RegistryLite
    -0.51
    MethodManager
    -0.50
    SBATCH
    -0.50
     iParam
    -0.50
     OnTrigger
    -0.50
    POSITIVE LOGITS
    About
    0.75
     About
    0.68
     Acerca
    0.67
    ABOUT
    0.65
     ABOUT
    0.64
    about
    0.57
    Acerca
    0.57
     about
    0.56
     identité
    0.47
    SOBRE
    0.46
    Activations Density 0.081%

    No Known Activations