© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2995
    Prev
    Next
    INDEX
    Explanations

    specific LaTeX formatting commands and spacing definitions in mathematical writing

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

    LaTeX spacing commands

    np_acts-logits-general · gemini-2.0-flash

    HTML tags and attributes

    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
    oredCriteria
    -0.82
     Roskov
    -0.73
    MessageTagHelper
    -0.70
    +#+#
    -0.69
    stateProvider
    -0.67
     Bioaccumulative
    -0.66
    libft
    -0.66
     mapStateToProps
    -0.66
     kasarigan
    -0.65
    principalColumn
    -0.65
    POSITIVE LOGITS
     colspan
    1.36
     rowspan
    0.95
    enumi
    0.64
     Morelos
    0.53
     two
    0.51
     waw
    0.47
    two
    0.46
    lji
    0.45
     محفوظة
    0.44
     divis
    0.43
    Activations Density 0.034%

    No Known Activations