© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4502
    Prev
    Next
    INDEX
    Explanations

    annotations related to nullability in code

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

    Java/Android code annotations like @NonNull, @Nullable, and Java keywords like static, private.

    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
    ngdoc
    -0.50
    hyrchwyd
    -0.36
    FlatStyle
    -0.36
    sizeCache
    -0.36
    AutoScaleMode
    -0.35
     Tasche
    -0.34
     <<<<<<<<<<<<<<
    -0.34
     Bühne
    -0.33
    ANTLR
    -0.32
     smtplib
    -0.32
    POSITIVE LOGITS
    NonNull
    2.16
    Nonnull
    1.30
    Nullable
    1.06
    NotNull
    1.01
    SuppressLint
    0.83
    BeginContext
    0.81
    requireNonNull
    0.72
    elemField
    0.71
    notNull
    0.65
    jetbrains
    0.62
    Activations Density 0.025%

    No Known Activations