© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10698
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate collaboration or association

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

    "With" followed by a noun phrase

    np_acts-logits-general · gemini-2.0-flash

    With a / an / the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toMatchSnapshot
    -0.56
    プライズ
    -0.52
    yyj
    -0.52
    ontale
    -0.52
    TagMode
    -0.50
    <bos>
    -0.50
     resourceCulture
    -0.49
    IsContent
    -0.49
     adipis
    -0.46
    ones
    -0.44
    POSITIVE LOGITS
     plenty
    0.83
     everyone
    0.77
     each
    0.76
    Aholisi
    0.74
     plans
    0.74
    ".
    0.72
     ciascuno
    0.69
     roots
    0.69
     lots
    0.69
     للاسماء
    0.69
    Activations Density 0.130%

    No Known Activations