Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10277
    Prev
    Next
    INDEX
    Explanations

    negative statements or expressions of dissatisfaction

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

    "at" or similar spellings

    np_acts-logits-general · gemini-2.0-flash

    at all

    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
    VIAF
    -0.88
    RegressionTest
    -0.84
    uxxxx
    -0.77
     дописавши
    -0.75
    DeleteBehavior
    -0.75
    ]--;
    -0.74
     مشين
    -0.73
    verständlich
    -0.73
    yntaxException
    -0.72
    }{*}{
    -0.71
    POSITIVE LOGITS
     at
    2.08
     whatsoever
    1.67
     At
    1.17
     affatto
    1.16
     AT
    1.15
    At
    1.07
    at
    1.03
     alls
    0.94
     כלל
    0.85
     בכל
    0.78
    Activations Density 0.183%

    No Known Activations