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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 5904
    Prev
    Next
    INDEX
    Explanations

    SQL query components and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atola
    -0.48
     pinulongan
    -0.47
     CGSize
    -0.45
    ivotopis
    -0.45
     AspNetCore
    -0.45
    ится
    -0.44
    vaz
    -0.43
    ActionCreators
    -0.42
    ()):
    -0.42
     BoxFit
    -0.42
    POSITIVE LOGITS
    ItemBackground
    0.79
     $_[
    0.76
     resourceCulture
    0.76
     getIntent
    0.65
     Requested
    0.65
     göm
    0.63
     témoin
    0.63
    thâu
    0.61
    Specify
    0.60
     Lorca
    0.59
    Activations Density 0.256%

    No Known Activations