Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 5979
    Prev
    Next
    INDEX
    Explanations

    references to numerical values and study results related to medical research

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

    Numbers within square brackets

    np_acts-logits-general · gemini-2.0-flash

    references citations numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.85
     protoimpl
    -0.81
    StructEnd
    -0.76
    IntoConstraints
    -0.75
     незавершена
    -0.75
     كومونز
    -0.70
    brainly
    -0.69
     geslacht
    -0.68
     оригіналу
    -0.67
    bootstrapcdn
    -0.65
    POSITIVE LOGITS
    9
    0.79
    6
    0.77
    5
    0.74
    8
    0.74
    7
    0.73
    4
    0.70
    3
    0.64
    2
    0.64
    1
    0.63
    0
    0.63
    Activations Density 1.010%

    No Known Activations