© 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. 3-GEMMASCOPE-RES-16K
    6. 5654
    Prev
    Next
    INDEX
    Explanations

    specific nouns and proper nouns related to individuals and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.70
     nakalista
    -0.68
    +#+#
    -0.67
     Autorizaciones
    -0.67
    ftagPool
    -0.65
    BagLayout
    -0.65
    httphttps
    -0.64
     Autorisations
    -0.63
    SBATCH
    -0.63
     ***!
    -0.63
    POSITIVE LOGITS
    ientôt
    0.40
    Enllaços
    0.35
     idéia
    0.33
    Története
    0.31
     organisation
    0.31
     Gött
    0.30
     exitos
    0.30
    لينكات
    0.30
     Италијани
    0.30
     ucz
    0.29
    Activations Density 3.072%

    No Known Activations