© 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. 608
    Prev
    Next
    INDEX
    Explanations

    references to pipetting, laboratory tools, and related methodologies in scientific contexts

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

    starting with "Ri*", "Pi*", "Si*", or "wi*"

    np_acts-logits-general · gemini-2.0-flash

    pip, rid, rig, rip

    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
     Moreau
    -0.57
    Brutal
    -0.52
    ArgsConstructor
    -0.52
     ausged
    -0.50
    Connell
    -0.49
    Ể
    -0.49
    ondy
    -0.48
    wahati
    -0.47
    lational
    -0.47
    ANDE
    -0.46
    POSITIVE LOGITS
    iti
    0.59
    itig
    0.56
     iload
    0.55
    iI
    0.52
     Putih
    0.51
    iid
    0.50
    Miri
    0.50
    getUid
    0.49
    ip
    0.48
    VIAF
    0.47
    Activations Density 1.607%

    No Known Activations