© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 2958
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditionality or dependency

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

    text document start markers or beginning-of-sequence tokens.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     weirdly
    -0.63
    redacted
    -0.62
     unnamed
    -0.60
     moitié
    -0.60
    Gizmos
    -0.60
    mappedBy
    -0.59
     oddly
    -0.58
     panicked
    -0.57
     makeshift
    -0.56
     bruised
    -0.55
    POSITIVE LOGITS
    省市镇
    0.62
    出版年
    0.61
    styleType
    0.57
     Ause
    0.55
    @[+][
    0.54
    LookAnd
    0.53
     estimés
    0.53
    RectangleBorder
    0.53
    addCriterion
    0.51
    ResponseWriter
    0.49
    Activations Density 2.747%

    No Known Activations