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. 1-GEMMASCOPE-RES-16K
    6. 6045
    Prev
    Next
    INDEX
    Explanations

    references to representation or advocacy on behalf of individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Skinner
    -0.59
    ganu
    -0.55
     OFDb
    -0.55
     brug
    -0.52
     Sena
    -0.51
     Was
    -0.51
    Creo
    -0.50
     produce
    -0.50
    anglès
    -0.49
     merce
    -0.49
    POSITIVE LOGITS
     behalf
    1.11
    harm
    0.93
     harm
    0.93
     Harm
    0.89
     harms
    0.84
    Harm
    0.73
     harmed
    0.73
    harmed
    0.72
     ReactDOM
    0.72
    WriteTagHelper
    0.70
    Activations Density 0.115%

    No Known Activations