© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 128212
    Prev
    Next
    INDEX
    Explanations

    references to manufacturer instructions and product manuals

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

    manufacturer instructions and manuals

    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
    Datuak
    -0.43
     kaarangay
    -0.36
    ፩
    -0.36
    ửi
    -0.36
    providedIn
    -0.35
    WriteTagHelper
    -0.35
     oprot
    -0.34
    Wil
    -0.34
    lesque
    -0.34
     Wil
    -0.34
    POSITIVE LOGITS
    存于互联网档案馆
    0.55
    astify
    0.54
     manufacturer
    0.53
     инструкции
    0.52
     Instruction
    0.51
     datasheet
    0.50
     instructions
    0.49
    ungsanleitung
    0.49
     instruction
    0.48
     manufacture
    0.48
    Activations Density 0.065%

    No Known Activations