© 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. 599
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming syntax

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

    code snippets and technical documentation, particularly related to programming languages like Swift, Java, and JavaScript.

    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
     EconPapers
    -1.16
     ویکی‌پدی
    -1.14
    GEBURTSDATUM
    -1.11
     zwiſchen
    -1.09
     kasarigan
    -1.06
    ſicht
    -1.05
    ロウィン
    -1.05
    <unused41>
    -1.05
    [@BOS@]
    -1.04
    <unused3>
    -1.04
    POSITIVE LOGITS
    The
    0.40
    These
    0.38
     with
    0.38
    This
    0.37
    With
    0.36
    Some
    0.35
    where
    0.35
    .
    0.35
    None
    0.34
    Using
    0.33
    Activations Density 0.316%

    No Known Activations