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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 82396
    Prev
    Next
    INDEX
    Explanations

    questions related to prime numbers and their factors

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

    prime factors and divisibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.84
    AddTagHelper
    -0.73
    rungsseite
    -0.64
     jsPsych
    -0.60
    MemoryWarning
    -0.58
    stateProvider
    -0.56
     contextLoads
    -0.55
    Билгалдахарш
    -0.54
    DebuggerNonUser
    -0.53
    RenderAtEndOf
    -0.52
    POSITIVE LOGITS
     cut
    0.31
     nakalista
    0.31
    畢竟
    0.30
    }?>
    0.30
     XNUMX
    0.29
     quoi
    0.29
     quest
    0.29
    ̈́
    0.28
    BibitemOpen
    0.28
    missao
    0.28
    Activations Density 0.081%

    No Known Activations