© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2710
    Prev
    Next
    INDEX
    Explanations

    noun phrases related to evaluation and judgment

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

    "...by the wayside" or "...air"

    np_acts-logits-general · gemini-2.0-flash

    by the wayside, out of thin air

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.61
    揄
    -0.59
     لينك
    -0.54
    onAttach
    -0.52
    posedge
    -0.51
    Atoi
    -0.51
    ActionCreators
    -0.50
    ViewImports
    -0.50
    elemField
    -0.49
    PreAuthorize
    -0.49
    POSITIVE LOGITS
    mtrl
    0.41
    Scooby
    0.41
    pecabe
    0.41
    zA
    0.40
    Lorem
    0.38
    Доброго
    0.38
    יתוף
    0.38
     нержа
    0.36
     Laissez
    0.35
    无所
    0.35
    Activations Density 1.770%

    No Known Activations