© 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. 14336
    Prev
    Next
    INDEX
    Explanations

    terms related to legal processes and documentation in a regulatory context

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

    time: "pending", "daily", "interim"

    np_acts-logits-general · gemini-2.0-flash

    interim or provisional states

    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
     PeEnEo
    -0.38
    AppMethodBeat
    -0.38
    Ehrungen
    -0.38
    RenderAtEndOf
    -0.38
    httphttps
    -0.37
    CharacterOffset
    -0.36
    Einzelnachweise
    -0.35
     CreateTagHelper
    -0.35
    Vegeu
    -0.35
     eens
    -0.34
    POSITIVE LOGITS
     interim
    0.59
     waiting
    0.52
     awaiting
    0.51
    abestanden
    0.51
     provisional
    0.51
    waiting
    0.50
    Waiting
    0.49
    Interim
    0.48
    PreExecute
    0.47
     meantime
    0.47
    Activations Density 0.482%

    No Known Activations