© 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. 98809
    Prev
    Next
    INDEX
    Explanations

    formal greetings and requests for assistance

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

    asking for help or explanations

    np_acts-logits-general · gemini-2.5-flash-lite

    sentences or phrases that express greetings, thanks, or polite forum-style salutations/closings.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     ویکی‌پدی
    -0.55
    ChildScrollView
    -0.54
    awtextra
    -0.54
    WriteTagHelper
    -0.51
    Décès
    -0.51
    AutoField
    -0.47
    EndGlobalSection
    -0.47
     ujednoznacz
    -0.47
     uitgenodigd
    -0.47
     typelib
    -0.45
    POSITIVE LOGITS
    richTextPanel
    0.50
    addGap
    0.41
    rament
    0.40
     Vario
    0.36
    assic
    0.36
    ologists
    0.35
    }*/
    0.34
    BLM
    0.34
    regierung
    0.34
    endphp
    0.34
    Activations Density 0.167%

    No Known Activations