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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9578
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and characteristics of physical models in relation to cosmic background radiation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oleum
    -0.48
    ICI
    -0.48
     stavu
    -0.46
     circumstantial
    -0.46
    ContextCompat
    -0.46
     Beatty
    -0.46
    assertRaises
    -0.45
    友
    -0.44
    icin
    -0.44
     tiros
    -0.44
    POSITIVE LOGITS
     scale
    1.60
     scales
    1.45
     Scale
    1.40
    scale
    1.37
     Scales
    1.32
     SCALE
    1.29
    Scale
    1.22
    scales
    1.18
     timescale
    1.17
     skala
    1.11
    Activations Density 0.777%

    No Known Activations