© 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. 55593
    Prev
    Next
    INDEX
    Explanations

    references to quantities, measurements, and types of methods in scientific contexts

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

    amount of method effect

    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
     ब्रेकडाउन
    -0.76
     AssemblyCulture
    -0.71
     otomatig
    -0.70
    AndEndTag
    -0.68
     nakalista
    -0.67
    ſelves
    -0.66
     jScrollPane
    -0.64
     <>",
    -0.63
    WithIOException
    -0.62
    ➟
    -0.62
    POSITIVE LOGITS
     dibawah
    0.38
     infecciones
    0.35
     dég
    0.35
     coté
    0.35
    ๊ก
    0.34
     उन्ह
    0.33
    PageRoute
    0.33
    使い方
    0.32
    Filmografia
    0.32
     didalam
    0.32
    Activations Density 0.254%

    No Known Activations