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. 11373
    Prev
    Next
    INDEX
    Explanations

    numerical data or parameters, particularly related to colors and specifications

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

    Numbers with a comma or dash

    np_acts-logits-general · gemini-2.0-flash

    numbers and symbols

    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
    mybatisplus
    -0.93
    abestanden
    -0.75
    Література
    -0.72
     indiri
    -0.69
    onViewCreated
    -0.66
    AndEndTag
    -0.65
    AddTagHelper
    -0.64
     indisponible
    -0.64
    DockStyle
    -0.63
    MLLoader
    -0.63
    POSITIVE LOGITS
     Cor
    0.50
    居
    0.48
    e
    0.48
    ErrorMessage
    0.47
    Cor
    0.47
     Theil
    0.46
    行
    0.44
    ogaster
    0.44
     Wors
    0.44
    em
    0.44
    Activations Density 0.483%

    No Known Activations