© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 10060
    Prev
    Next
    INDEX
    Explanations

    the presence of statistics related to social issues and community dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Randall
    -0.79
     regia
    -0.79
     Races
    -0.78
     raced
    -0.77
    Races
    -0.76
    Rural
    -0.75
     renderer
    -0.75
     Roux
    -0.74
     Richards
    -0.73
     radiators
    -0.73
    POSITIVE LOGITS
    IsContent
    0.50
    ContentAsync
    0.47
    EnableWeb
    0.43
    =============
    0.43
     المعيارى
    0.42
    specialchars
    0.42
    HttpClientModule
    0.41
    Hochspringen
    0.41
    UDAD
    0.40
    ============
    0.39
    Activations Density 0.623%

    No Known Activations