© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 121559
    Prev
    Next
    INDEX
    Explanations

    grammatical terms and their classifications

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

    grammatical definitions and linguistic distinctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lance
    -0.39
     port
    -0.38
    Lance
    -0.36
    loth
    -0.36
     Mand
    -0.34
     case
    -0.34
     off
    -0.31
     Lancer
    -0.31
     نه
    -0.30
     compliant
    -0.30
    POSITIVE LOGITS
    GEBURTSDATUM
    0.76
     ModelExpression
    0.73
     يتيمه
    0.73
    ंदीखरीदारी
    0.69
    UseVisualStyle
    0.65
    Життєпис
    0.63
    IUrlHelper
    0.61
    httphttps
    0.60
    Hochspringen
    0.58
     оригіналу
    0.57
    Activations Density 0.442%

    No Known Activations