Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11677
    Prev
    Next
    INDEX
    Explanations

    biographical details about an individual

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     squeak
    -0.49
     dile
    -0.46
     quasi
    -0.45
    Margin
    -0.42
     Ef
    -0.42
    ########.
    -0.42
     recourse
    -0.41
     margin
    -0.41
     rhyme
    -0.41
    دانشنامهٔ
    -0.41
    POSITIVE LOGITS
     hobbies
    0.57
     كومونز
    0.56
     auroit
    0.53
    PMailer
    0.48
     StatelessWidget
    0.47
     hjär
    0.46
    providedIn
    0.46
     AppCompatTheme
    0.45
     étoit
    0.44
    AnimationsModule
    0.44
    Activations Density 0.007%

    No Known Activations