© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6575
    Prev
    Next
    INDEX
    Explanations

    cooking-related actions and instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding adjectives ending in "-est" or "-ed"

    np_acts-logits-general · gemini-2.0-flash

    cooking states and completion

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     currently
    -0.48
    fillType
    -0.47
    httphttps
    -0.44
     kasarigan
    -0.38
     AssemblyVersion
    -0.37
     presently
    -0.37
    attuale
    -0.36
     margiela
    -0.36
     clearfix
    -0.36
    arraycopy
    -0.35
    POSITIVE LOGITS
    neté
    0.41
    IUrlHelper
    0.40
    ModelSerializer
    0.39
    WebElementEntity
    0.38
     gruesa
    0.38
    Perfection
    0.38
    Fully
    0.38
    findpost
    0.38
    archiviato
    0.37
    ough
    0.37
    Activations Density 0.125%

    No Known Activations