© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11303
    Prev
    Next
    INDEX
    Explanations

    programming and code-related constructs, particularly focusing on logging and data structures

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

    Code elements (e.g., Logger, stat, argc)

    np_acts-logits-general · gemini-2.0-flash

    function arguments and system calls

    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
    stdc
    -0.51
    stes
    -0.41
    SpringBootTest
    -0.40
    RSV
    -0.40
    aster
    -0.40
    kijken
    -0.40
    <?
    -0.39
    ılığı
    -0.39
    ster
    -0.39
     lighten
    -0.39
    POSITIVE LOGITS
     كومونز
    0.62
    FormTagHelper
    0.61
     WebDriverWait
    0.59
    RTLI
    0.57
    下载附件
    0.57
     Chwiliwch
    0.57
     يتيمه
    0.56
    hoeddwyd
    0.55
     pinulongan
    0.53
    Chham
    0.52
    Activations Density 0.205%

    No Known Activations