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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23-GEMMASCOPE-RES-16K
    6. 12340
    Prev
    Next
    INDEX
    Explanations

    assertive statements or claims about situations and events

    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
     <=",
    -0.96
     nahilalakip
    -0.84
    
    -0.80
     kaarangay
    -0.77
    Composable
    -0.76
    AndEndTag
    -0.74
    ThroughAttribute
    -0.65
    исленность
    -0.64
    Прият
    -0.62
    ContentAlignment
    -0.62
    POSITIVE LOGITS
     incredible
    1.52
     unbelievable
    1.45
     amazing
    1.44
     phenomenal
    1.44
     extraordinary
    1.39
     astounding
    1.36
     AMAZING
    1.30
     astonishing
    1.29
     Incredible
    1.26
    incredible
    1.25
    Activations Density 0.404%

    No Known Activations