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. 3-GEMMASCOPE-RES-16K
    6. 10033
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups in a general context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagHelpers
    -0.88
    Mot
    -0.74
    かせて
    -0.73
    UnusedPrivate
    -0.72
     Mot
    -0.68
    らせて
    -0.68
     Spire
    -0.67
    lux
    -0.66
    setX
    -0.64
    tx
    -0.63
    POSITIVE LOGITS
     anyone
    3.06
    anyone
    2.94
     Anyone
    2.79
    Anyone
    2.74
     anybody
    2.69
     ANYONE
    2.57
     Anybody
    2.55
    Anybody
    2.46
     everyone
    1.91
     someone
    1.84
    Activations Density 0.045%

    No Known Activations