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. 25-GEMMASCOPE-RES-16K
    6. 1865
    Prev
    Next
    INDEX
    Explanations

    specific structural or performance-related metrics related to processes or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $_['
    -0.67
     snippetHide
    -0.57
     OMITBAD
    -0.57
    IndentedString
    -0.56
    Spoljašnje
    -0.56
     виправивши
    -0.55
    Vidite
    -0.55
    Референце
    -0.55
    DateTimeField
    -0.52
    assword
    -0.51
    POSITIVE LOGITS
     kasarigan
    0.51
    RectangleBorder
    0.50
     onPostExecute
    0.46
     AssemblyTitle
    0.45
    BindingResult
    0.44
    ConstraintMaker
    0.44
    __((
    0.43
    //
    0.42
    WebControls
    0.42
    centralwidget
    0.42
    Activations Density 0.281%

    No Known Activations