Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 415
    Prev
    Next
    INDEX
    Explanations

    questions regarding future events and their potential outcomes

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

    hypothetical scenarios involving causality or potential outcomes, particularly when asking "what would/could happen".

    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
    <unused14>
    -0.89
    <pad>
    -0.89
    <unused79>
    -0.89
    OGND
    -0.89
    <unused28>
    -0.89
    <unused41>
    -0.89
    <unused16>
    -0.89
    <unused17>
    -0.89
    <unused8>
    -0.89
    <unused3>
    -0.89
    POSITIVE LOGITS
     status
    0.45
     if
    0.44
     situation
    0.41
     concerning
    0.40
     regarding
    0.40
     when
    0.40
     relation
    0.38
     fate
    0.36
    if
    0.36
    status
    0.35
    Activations Density 0.321%

    No Known Activations