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. 8947
    Prev
    Next
    INDEX
    Explanations

    references to damage and its effects

    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
    abestanden
    -0.64
    setVerticalGroup
    -0.59
    stateProvider
    -0.53
    ições
    -0.51
    AndEndTag
    -0.50
    Према
    -0.50
     banger
    -0.48
     menudo
    -0.48
    fxml
    -0.47
    atorship
    -0.47
    POSITIVE LOGITS
     inflicted
    1.11
     done
    1.00
     sustained
    0.95
     suffered
    0.85
    done
    0.81
     DONE
    0.77
     caused
    0.76
     dealt
    0.76
     Done
    0.74
     incurred
    0.72
    Activations Density 0.228%

    No Known Activations