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. 16-GEMMASCOPE-RES-16K
    6. 14962
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Word after "is," "the," "ub" or before "impacts"

    np_acts-logits-general · gemini-2.0-flash

    impacts and mitigation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useRouter
    -0.68
     defaultstate
    -0.66
     >=",
    -0.58
    rungsseite
    -0.57
     furiously
    -0.53
     nakalista
    -0.52
    matum
    -0.51
     beginners
    -0.50
     experiment
    -0.47
     experimento
    -0.47
    POSITIVE LOGITS
     impacts
    0.74
     mitigation
    0.72
     entlang
    0.67
     Mitigation
    0.66
    Mitigation
    0.64
    posedge
    0.63
     mitig
    0.58
    GEBURTSDATUM
    0.58
     Impacts
    0.57
    ktır
    0.57
    Activations Density 0.148%

    No Known Activations