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. 13-GEMMASCOPE-RES-16K
    6. 15979
    Prev
    Next
    INDEX
    Explanations

    terms related to ranking and classification systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.82
     _('
    -0.70
    EObject
    -0.67
    verwijspagina
    -0.65
    liquer
    -0.65
     darbu
    -0.65
     onPostExecute
    -0.64
     PLW
    -0.64
     Gaby
    -0.64
    wiada
    -0.62
    POSITIVE LOGITS
     RANK
    1.39
     Rankin
    1.27
    rank
    1.25
     ranks
    1.22
     rank
    1.21
     Rank
    1.20
    Rank
    1.18
    RANK
    1.17
     Ranks
    1.16
     ranking
    1.15
    Activations Density 0.096%

    No Known Activations