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. 6943
    Prev
    Next
    INDEX
    Explanations

    code snippets related to dynamic HTML manipulation

    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
    ActionCreators
    -0.72
     transférez
    -0.66
    Rhestr
    -0.65
    Personensuche
    -0.63
    principalTable
    -0.62
    MockBean
    -0.62
    PHeader
    -0.61
     <=",
    -0.61
    ValueStyle
    -0.60
     Malabar
    -0.60
    POSITIVE LOGITS
     monta
    0.57
     snabb
    0.56
     hängt
    0.52
     montagem
    0.52
    onAdd
    0.51
    blij
    0.51
    inflate
    0.50
     kwamba
    0.48
     bevestig
    0.48
    只见
    0.47
    Activations Density 0.138%

    No Known Activations