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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114239
    Prev
    Next
    INDEX
    Explanations

    the indefinite article "a" and its variations

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

    a/an or more followed by descriptor

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    spyOn
    -0.58
    cipital
    -0.48
    stig
    -0.46
    espero
    -0.46
    missing
    -0.46
    isempty
    -0.45
    crazy
    -0.45
     tags
    -0.44
     tag
    -0.44
     Gul
    -0.44
    POSITIVE LOGITS
    awtextra
    0.59
    addCriterion
    0.59
     healthier
    0.58
    ImageContext
    0.58
    AxisAlignment
    0.58
     Offisielt
    0.57
     healthy
    0.54
    RTSC
    0.52
     useAppContext
    0.52
    ⟬
    0.52
    Activations Density 0.016%

    No Known Activations