© 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
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 2985
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ents."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rostros
    -0.40
     gostar
    -0.38
     steward
    -0.38
     îns
    -0.37
     spoke
    -0.35
     Sosten
    -0.33
     oś
    -0.33
     veux
    -0.32
    Cuánt
    -0.32
     yarar
    -0.32
    POSITIVE LOGITS
     styling
    0.72
    Platinum
    0.72
     Pt
    0.71
     styl
    0.71
    styling
    0.70
    Colony
    0.68
     confin
    0.68
    confined
    0.67
    Attached
    0.66
     confinement
    0.66
    Activations Density 0.218%

    No Known Activations