© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2403
    Prev
    Next
    INDEX
    Explanations

    terms related to diffusion and its effects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    salm
    -0.50
    amak
    -0.48
    geving
    -0.48
    comy
    -0.47
    witcher
    -0.46
    lammatory
    -0.46
    ddy
    -0.46
    κια
    -0.45
    aterally
    -0.45
    thoscope
    -0.45
    POSITIVE LOGITS
     occurs
    0.91
     phenomena
    0.90
     occurring
    0.87
     phenomenon
    0.86
     occur
    0.81
     occurred
    0.78
    occurs
    0.77
     happening
    0.74
     rate
    0.72
     occured
    0.70
    Activations Density 1.230%

    No Known Activations