© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13979
    Prev
    Next
    INDEX
    Explanations

    code-related syntax elements and structure in programming languages

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

    Citations or references with bracketed names

    np_acts-logits-general · gemini-2.0-flash

    thm:sec, thm:code2000 theory2 err zero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.70
    +:+
    -0.56
     referrerpolicy
    -0.55
    PerformLayout
    -0.54
     kasarigan
    -0.53
     jsPsych
    -0.52
    ⤹
    -0.50
    AddTagHelper
    -0.50
    fromnode
    -0.50
    .*")]
    -0.49
    POSITIVE LOGITS
    memberof
    0.53
    haikusbot
    0.51
    NewLabel
    0.49
    wantErr
    0.47
    RegressionTest
    0.45
     كومونز
    0.41
    meldet
    0.41
    WindowConstants
    0.40
     dụ
    0.40
    bands
    0.40
    Activations Density 0.522%

    No Known Activations