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. 11-GEMMASCOPE-RES-16K
    6. 1965
    Prev
    Next
    INDEX
    Explanations

    concepts related to measurements and evaluations in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })*/
    -0.81
     AssemblyTitle
    -0.74
    ніципа
    -0.67
    MENAFN
    -0.66
    Билгалдахарш
    -0.65
    Autoritní
    -0.64
     <=",
    -0.64
    Bibliograf
    -0.64
    omenclature
    -0.63
    źć
    -0.61
    POSITIVE LOGITS
    تقاوى
    0.50
    enumi
    0.50
     становника
    0.48
    soort
    0.48
    itemBuilder
    0.48
    stateMutability
    0.47
    EDEFAULT
    0.46
    Gweler
    0.45
    CloseOperation
    0.44
     AssemblyVersion
    0.43
    Activations Density 1.356%

    No Known Activations