© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2391
    Prev
    Next
    INDEX
    Explanations

    references to people or groups involved in various contexts or actions

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

    phrases about people doing or experiencing things, especially related to action words like "who can/want/think/do".

    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
     none
    -0.35
    .
    -0.32
     another
    -0.32
     S
    -0.32
    another
    -0.31
     and
    -0.31
     several
    -0.30
     or
    -0.29
     for
    -0.28
    S
    -0.28
    POSITIVE LOGITS
    ésultats
    0.76
    <unused80>
    0.75
    <unused8>
    0.75
    <unused23>
    0.75
    <unused42>
    0.75
    <pad>
    0.75
    <unused68>
    0.75
    <unused79>
    0.75
    <unused74>
    0.75
    [@BOS@]
    0.75
    Activations Density 0.237%

    No Known Activations