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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 40112
    Prev
    Next
    INDEX
    Explanations

    conversational phrases and expressions of uncertainty or questioning attitude

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

    あ and its following particle

    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
     ISNI
    -0.67
     kasarigan
    -0.65
     Chwiliwch
    -0.61
     Administrativna
    -0.60
    AndEndTag
    -0.59
    帖最后由
    -0.58
    ulemon
    -0.58
    
    -0.57
    MockBean
    -0.57
    FXML
    -0.56
    POSITIVE LOGITS
    <bos>
    0.46
     Pringle
    0.40
     Houſe
    0.40
     others
    0.40
     okrąg
    0.38
     Strickland
    0.38
     rahasia
    0.37
     Prancis
    0.37
     quede
    0.36
    </table>
    0.36
    Activations Density 0.050%

    No Known Activations