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. 6054
    Prev
    Next
    INDEX
    Explanations

    queries or requests for information or explanations regarding a topic

    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
    offsetof
    -0.65
    حوالہ
    -0.64
    enumi
    -0.60
    HomeAsUpEnabled
    -0.55
     MainAxisSize
    -0.54
    enumii
    -0.54
     Vielzahl
    -0.53
     seules
    -0.52
    neither
    -0.52
    AndEndTag
    -0.52
    POSITIVE LOGITS
     some
    3.87
    some
    3.07
    Some
    2.85
     Some
    2.82
     SOME
    2.41
    SOME
    2.28
     algunos
    2.04
     algunas
    1.94
     alguns
    1.94
     algumas
    1.91
    Activations Density 1.070%

    No Known Activations