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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1970
    Prev
    Next
    INDEX
    Explanations

    function calls related to controlling LEDs and their states

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

    Code snippets ending in parentheses or semicolons

    np_acts-logits-general · gemini-2.0-flash

    closing parentheses

    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
    ConstraintMaker
    -1.19
    ValueStyle
    -1.11
     GenerationType
    -1.10
     незавершена
    -1.09
    SBATCH
    -1.09
    NUMX
    -1.08
     itſelf
    -1.05
    GraphicsUnit
    -1.04
    LookAnd
    -1.03
    principalColumn
    -1.03
    POSITIVE LOGITS
    .
    0.81
    <eos>
    0.80
    ↵↵
    0.64
    ,
    0.60
    ↵
    0.56
     because
    0.56
    !
    0.54
     and
    0.52
     after
    0.49
    :
    0.49
    Activations Density 0.102%

    No Known Activations