© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 455
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and terminology, particularly concerning object and view management

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

    programming syntax and code-related elements, particularly in JavaScript or a similar language.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    MockBean
    -0.42
    runOnUiThread
    -0.36
     >::
    -0.33
    inflater
    -0.32
     Games
    -0.32
     sponsors
    -0.30
     gql
    -0.30
     ویکی‌آمباردا
    -0.30
     sponsor
    -0.29
    NSIndexPath
    -0.29
    POSITIVE LOGITS
    RegressionTest
    0.68
    httphttps
    0.65
    IVEREF
    0.65
    ngdoc
    0.57
    ChildScrollView
    0.56
    RetentionPolicy
    0.53
    usable
    0.52
    RenderAtEndOf
    0.51
    mphony
    0.50
    ReusableCell
    0.50
    Activations Density 0.252%

    No Known Activations