© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 2093
    Prev
    Next
    INDEX
    Explanations

    names of people and film-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.47
     distanciation
    -0.40
     Nacionales
    -0.38
    AddAttribute
    -0.38
     arşivlendi
    -0.37
    ernoo
    -0.37
    ükemmel
    -0.35
    iprot
    -0.35
    rungsseite
    -0.34
    cookieParser
    -0.34
    POSITIVE LOGITS
     Italijanski
    0.60
     lenker
    0.45
    TagHelpers
    0.42
     مرئيه
    0.41
    RTLR
    0.41
    webElementGuid
    0.41
    ErrUnexpectedEOF
    0.40
    tative
    0.40
    hebt
    0.40
    personalised
    0.39
    Activations Density 0.101%

    No Known Activations