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. 8-GEMMASCOPE-RES-16K
    6. 2087
    Prev
    Next
    INDEX
    Explanations

    specific measurements and concentrations in scientific protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.86
    AccessorTable
    -0.85
    expandindo
    -0.83
    bitat
    -0.81
    +#+#
    -0.73
    ("")]
    
    -0.72
    Portale
    -0.72
    IsContent
    -0.71
    })->
    -0.70
     StringTokenizer
    -0.70
    POSITIVE LOGITS
     opzioni
    0.47
    attributes
    0.47
    options
    0.46
     kapasitas
    0.45
     prøve
    0.45
    psack
    0.44
     completos
    0.44
    følgelig
    0.42
    ppure
    0.42
     günü
    0.42
    Activations Density 0.509%

    No Known Activations