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. 22-GEMMASCOPE-RES-16K
    6. 11106
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions and relationships involving properties of algebraic structures and functions

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

    Comes after the word "the" in mathematical or logical expressions

    np_acts-logits-general · gemini-2.0-flash

    corresponding coefficient values

    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
    many
    -0.47
    once
    -0.46
    nsec
    -0.46
     llegue
    -0.44
    mostly
    -0.43
     podr
    -0.43
    fla
    -0.42
     tiende
    -0.41
    tative
    -0.40
    ったり
    -0.40
    POSITIVE LOGITS
     corresponding
    0.85
     corrispond
    0.78
     expression
    0.77
     EconPapers
    0.76
     sum
    0.75
    enterOuterAlt
    0.74
    Amicalement
    0.73
    DockStyle
    0.72
     resulting
    0.72
     value
    0.72
    Activations Density 1.131%

    No Known Activations