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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10798
    Prev
    Next
    INDEX
    Explanations

    code-related syntax elements and operations

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

    Code snippets, variables, and data types

    np_acts-logits-general · gemini-2.0-flash

    numeric operations and assignments

    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
     %@",
    -0.61
     beginnetje
    -0.57
     autorytatywna
    -0.56
    BeginInit
    -0.55
    KEYCODE
    -0.53
    DockStyle
    -0.53
    fitrión
    -0.51
    GHIJKLM
    -0.51
    (@"%@",
    -0.50
     مشين
    -0.50
    POSITIVE LOGITS
    NSNumber
    0.72
     numbers
    0.66
     numeric
    0.64
    vician
    0.63
     nubes
    0.62
    isNaN
    0.61
    ArrowToggle
    0.59
    intval
    0.58
     PyLong
    0.58
     sappiamo
    0.57
    Activations Density 0.148%

    No Known Activations