© 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. 10771
    Prev
    Next
    INDEX
    Explanations

    action verbs associated with analysis or evaluation

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    analysis and evaluation verbs

    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
    genie
    -0.49
     ſche
    -0.48
    prägt
    -0.47
    Waga
    -0.46
     anhänger
    -0.45
     вікісторінку
    -0.44
     your
    -0.42
    URSS
    -0.42
    loon
    -0.42
     eyelash
    -0.42
    POSITIVE LOGITS
    isContained
    0.59
    toHaveBeenCalled
    0.59
    ized
    0.59
    tioned
    0.57
    ferred
    0.57
    ensed
    0.56
    acted
    0.56
    cted
    0.56
    entered
    0.55
    keted
    0.55
    Activations Density 1.352%

    No Known Activations