© 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. 9107
    Prev
    Next
    INDEX
    Explanations

    names and specific characteristics of individuals

    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
     Had
    -0.43
     Automobile
    -0.40
     Homes
    -0.40
     FishBase
    -0.40
     Her
    -0.40
     Boi
    -0.39
    auto
    -0.39
    Blonde
    -0.38
     HOMES
    -0.38
    Automobile
    -0.38
    POSITIVE LOGITS
     صوتيه
    0.67
     myſelf
    0.64
    AutoScaleMode
    0.61
     disambiguazione
    0.57
     autorytatywna
    0.57
    ViewImports
    0.55
     itſelf
    0.53
     للمعارف
    0.52
    ChildScrollView
    0.52
    +#+#
    0.52
    Activations Density 1.953%

    No Known Activations