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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12309
    Prev
    Next
    INDEX
    Explanations

    references to individuals associated with academic qualifications and institutions

    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
     препратки
    -0.75
    AndEndTag
    -0.73
    Jeografia
    -0.73
    ніципалі
    -0.72
     للمعارف
    -0.70
    awtextra
    -0.67
    ArgsConstructor
    -0.66
     purpoſe
    -0.65
    })();
    
    -0.64
     Anſ
    -0.63
    POSITIVE LOGITS
     see
    0.49
     tag
    0.48
     kind
    0.48
     seal
    0.44
     peaks
    0.44
     rõ
    0.42
     väli
    0.42
     aikaa
    0.41
     organise
    0.41
    Välislingid
    0.40
    Activations Density 0.068%

    No Known Activations