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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 10468
    Prev
    Next
    INDEX
    Explanations

    the term "across" indicating a focus on comparative or widespread themes

    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
    tanooga
    -0.75
     kasarigan
    -0.70
    тература
    -0.69
    lotl
    -0.67
     отношению
    -0.65
     ISU
    -0.64
    ulz
    -0.64
    UTERS
    -0.63
     образом
    -0.62
    ResponseEntity
    -0.61
    POSITIVE LOGITS
     Across
    2.11
     ACROSS
    2.08
    Across
    2.05
     across
    2.04
    across
    2.03
    ROSS
    1.14
    throughout
    1.12
     عبر
    1.09
     throughout
    1.06
     Throughout
    1.04
    Activations Density 0.039%

    No Known Activations