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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6234
    Prev
    Next
    INDEX
    Explanations

    references to the Peugeot SUV and its features or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.63
    GEBURTSDATUM
    -0.59
     CreateTagHelper
    -0.58
     OMITBAD
    -0.52
    Diwedd
    -0.52
    extAlignment
    -0.51
    Халык
    -0.51
    illotine
    -0.50
    lanations
    -0.50
    tonode
    -0.49
    POSITIVE LOGITS
    Rüyada
    0.46
     "..\..\
    0.42
    AppMethodBeat
    0.37
    تقاوى
    0.36
    providedIn
    0.33
     AssemblyProduct
    0.30
    chequer
    0.30
     NgModule
    0.29
     superior
    0.29
    InputModule
    0.29
    Activations Density 0.160%

    No Known Activations