© 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. 24-GEMMASCOPE-RES-16K
    11. 16144
    Prev
    Next
    INDEX
    Explanations

    the presence of the name "Giunta" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Capitalized two-letter sequences

    np_acts-logits-general · gemini-2.0-flash

    Giuliani, Giunta, Giacinto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षाओं
    -0.62
    contentLoaded
    -0.55
     uLocal
    -0.54
    prepareStatement
    -0.52
    rungsseite
    -0.52
    AutoresizingMask
    -0.50
    UrlEncoded
    -0.49
    tidase
    -0.49
    })$}
    -0.48
    ScopeManager
    -0.48
    POSITIVE LOGITS
     HasFactory
    0.59
    gantes
    0.53
     CascadeType
    0.53
     ब्रेकडाउन
    0.52
    новништво
    0.52
    MNA
    0.51
    psum
    0.51
    orgi
    0.50
    出版年
    0.50
    ipfel
    0.50
    Activations Density 0.168%

    No Known Activations