© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 110318
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming-related content

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

    continuation and continued actions

    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
    Personendaten
    -0.65
    MessageTagHelper
    -0.59
    LookAnd
    -0.57
    StoryboardSegue
    -0.53
    ftagPool
    -0.53
    ArgsConstructor
    -0.52
    AccessorTable
    -0.52
     gelukkig
    -0.48
    MemoryWarning
    -0.46
    findpost
    -0.46
    POSITIVE LOGITS
     continued
    0.56
     continuation
    0.52
     continue
    0.52
     continuing
    0.50
     ادامه
    0.49
     continues
    0.48
    continued
    0.48
    继续
    0.47
     continu
    0.46
     Continuation
    0.46
    Activations Density 0.001%

    No Known Activations