© 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. 125085
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and terms related to scientific concepts

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

    exponential decay

    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
    ⓧ
    -0.70
    MessageTagHelper
    -0.68
     betweenstory
    -0.61
    ItemBackground
    -0.59
     """",
    -0.58
    webElementXpaths
    -0.57
     Italijani
    -0.57
    govina
    -0.57
    providedIn
    -0.56
    SourceChecksum
    -0.55
    POSITIVE LOGITS
    HasAnnotation
    1.48
     незавершена
    0.53
    ValueStyle
    0.38
     substantially
    0.31
    jfree
    0.31
     Denn
    0.30
    LLocation
    0.30
    styleable
    0.29
    GraphicsUnit
    0.28
     science
    0.28
    Activations Density 0.000%

    No Known Activations