© 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. 24-GEMMASCOPE-RES-16K
    11. 14678
    Prev
    Next
    INDEX
    Explanations

    references to software, including names of applications, versions, and any related technical terms

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

    Code and non-English text

    np_acts-logits-general · gemini-2.0-flash

    programming, math, and text delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     said
    -0.73
    said
    -0.73
    and
    -0.70
    in
    -0.70
    as
    -0.68
    is
    -0.67
    or
    -0.66
    to
    -0.63
    then
    -0.63
    into
    -0.63
    POSITIVE LOGITS
     Normdatei
    0.97
     Efq
    0.86
    Chham
    0.82
    WriteTagHelper
    0.82
    /−
    0.81
    SBATCH
    0.81
     виправивши
    0.80
    DeleteBehavior
    0.80
    SupportActionBar
    0.78
     jsPsych
    0.78
    Activations Density 0.090%

    No Known Activations