© 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. 477
    Prev
    Next
    INDEX
    Explanations

    technical queries and troubleshooting related to computer systems or programming

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

    Uncertainty, speculation, or possibility

    np_acts-logits-general · gemini-2.0-flash

    possibly a culprit

    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
     HasFactory
    -0.78
     Houſe
    -0.72
    styleType
    -0.72
    inSlope
    -0.65
     ſind
    -0.62
    outWeight
    -0.62
    estroyer
    -0.59
    nthetic
    -0.59
     ब्रेकडाउन
    -0.59
    AddTagHelper
    -0.58
    POSITIVE LOGITS
     culprit
    0.40
    perhaps
    0.38
    possibly
    0.35
     culprits
    0.33
     possibly
    0.33
     perhaps
    0.31
     responsables
    0.30
    maybe
    0.30
     numerus
    0.29
     responsable
    0.29
    Activations Density 1.052%

    No Known Activations