© 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 EvalsExportsinterp-engineNEWAPI 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. 16319
    Prev
    Next
    INDEX
    Explanations

    SQL commands and database creation terms

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

    Text preceding a reference (e.g., Fig. 1B)

    np_acts-logits-general · gemini-2.0-flash

    similarity and equivalence

    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
     saites
    -0.66
    RenderAtEndOf
    -0.64
     Normdatei
    -0.63
    IVEREF
    -0.61
    verwijspagina
    -0.61
    ロウィン
    -0.59
    ⓧ
    -0.58
    InputTagHelper
    -0.54
     المعيارى
    -0.52
    saraba
    -0.52
    POSITIVE LOGITS
     similar
    0.49
     similarly
    0.44
     likewise
    0.39
    Similar
    0.35
    similar
    0.35
     same
    0.35
     equivalent
    0.35
     meant
    0.34
     Similarly
    0.34
     podob
    0.33
    Activations Density 1.319%

    No Known Activations