Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 81525
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals and entities, particularly in scientific and legal contexts

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

    acronyms and names

    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
    ichthys
    -0.38
     Montoya
    -0.38
    ceğine
    -0.37
     raconter
    -0.37
     Zuw
    -0.36
    MathML
    -0.36
     niew
    -0.36
     pribadi
    -0.35
     detalles
    -0.35
     McFarland
    -0.35
    POSITIVE LOGITS
     $_"
    0.85
     $_(
    0.75
     Hibernate
    0.73
    copg
    0.72
     Monfieur
    0.71
    hibernate
    0.69
     Equinox
    0.68
     faſt
    0.68
    ſelves
    0.66
     Mousse
    0.66
    Activations Density 0.383%

    No Known Activations