© 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. 18-GEMMASCOPE-RES-16K
    11. 935
    Prev
    Next
    INDEX
    Explanations

    elements related to networking and data structure initialization in programming code

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

    `sizeof` calls, often related to structures

    np_acts-logits-general · gemini-2.0-flash

    calculating sizes in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shell
    -0.62
     Shell
    -0.56
    shell
    -0.56
     command
    -0.54
    Shell
    -0.54
    loon
    -0.52
    command
    -0.51
     Shells
    -0.50
     shells
    -0.50
     commandes
    -0.49
    POSITIVE LOGITS
     sizeof
    1.59
    sizeof
    1.50
    offsetof
    1.05
    ValueStyle
    0.93
    setof
    0.73
    NUMX
    0.67
    TestingModule
    0.65
    providedIn
    0.64
    PerformLayout
    0.63
    ReusableCell
    0.62
    Activations Density 0.469%

    No Known Activations