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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 11855
    Prev
    Next
    INDEX
    Explanations

    terms related to function arguments and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JpaRepository
    -0.65
    </table>
    -0.56
    SSN
    -0.56
     Ause
    -0.56
    NotFoundError
    -0.55
     Extragalactic
    -0.54
    rizona
    -0.53
    EditorBrowsable
    -0.51
    ыгана
    -0.50
    uoco
    -0.50
    POSITIVE LOGITS
     parameter
    0.83
     argument
    0.80
     arguments
    0.78
     getopt
    0.76
     arg
    0.76
     nargin
    0.75
     PARAMETER
    0.75
    arg
    0.75
     parameters
    0.74
    RequestParam
    0.73
    Activations Density 0.438%

    No Known Activations