© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 5900
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and data structures

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

    empty string or null

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دیکھیے
    -0.49
     يتيمه
    -0.47
    AddHtmlAttribute
    -0.42
    HomeAsUpEnabled
    -0.40
    емость
    -0.38
     prisa
    -0.36
     BoxDecoration
    -0.35
    BufferedReader
    -0.35
     zamanda
    -0.35
    HasIndex
    -0.35
    POSITIVE LOGITS
     null
    1.15
     empty
    1.10
     Null
    1.00
     zero
    0.99
     NULL
    0.99
    null
    0.95
     blank
    0.94
     nothing
    0.93
    Null
    0.93
     nil
    0.92
    Activations Density 0.230%

    No Known Activations