© 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. 579
    Prev
    Next
    INDEX
    Explanations

    scientific evidence and validation of hypotheses in research studies

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

    Verifying research or medical findings

    np_acts-logits-general · gemini-2.0-flash

    verify and confirm

    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
     ſta
    -0.77
     pleaſure
    -0.77
     ſy
    -0.75
     ſte
    -0.72
    ſelves
    -0.71
     ſtre
    -0.69
     ſche
    -0.69
    ſelf
    -0.69
     ſch
    -0.69
     cherchés
    -0.67
    POSITIVE LOGITS
     inspect
    0.36
     verified
    0.35
     dug
    0.34
     verify
    0.33
     confirm
    0.33
    inspect
    0.32
     confront
    0.32
    verify
    0.31
     véri
    0.31
     check
    0.29
    Activations Density 0.680%

    No Known Activations