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-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53461
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to options or configurations in a code context

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

    code and mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.91
     препратки
    -0.75
     '\\;'
    -0.75
    findpost
    -0.72
    EndGlobalSection
    -0.71
    AndEndTag
    -0.63
    DAOImpl
    -0.61
     beginnetje
    -0.61
    )$_
    -0.60
     Theſe
    -0.59
    POSITIVE LOGITS
    WEBPACK
    0.55
     graines
    0.49
    pstead
    0.48
    scanf
    0.46
     ingredienti
    0.44
     matang
    0.44
    FormTagHelper
    0.44
    peras
    0.44
     stället
    0.43
    manda
    0.43
    Activations Density 0.034%

    No Known Activations