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 - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12155
    Prev
    Next
    INDEX
    Explanations

    keywords related to parameters and private functions in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saites
    -0.72
    imanapun
    -0.71
     surla
    -0.70
    PreInfinity
    -0.69
    ValueStyle
    -0.69
    diyesi
    -0.68
     BorderRadius
    -0.67
     BIBSYS
    -0.66
    NewUrlParser
    -0.66
    ########.
    -0.66
    POSITIVE LOGITS
    NUMX
    0.55
     Podemos
    0.52
     excru
    0.50
    kore
    0.49
    InlineData
    0.49
    !("
    0.49
    Попис
    0.48
     Acha
    0.46
     seder
    0.45
    Composable
    0.44
    Activations Density 0.311%

    No Known Activations