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. 411
    Prev
    Next
    INDEX
    Explanations

    terms related to power dynamics and authority

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

    hypothetical scenarios and speculative language about potential actions or outcomes.

    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
    webElementXpaths
    -0.54
     فريبيس
    -0.53
    Tazama
    -0.51
    BagLayout
    -0.50
     gren
    -0.38
    ])):
    -0.38
    mozilla
    -0.37
    Traditional
    -0.37
    eschou
    -0.37
    íqu
    -0.37
    POSITIVE LOGITS
     would
    0.81
    would
    0.60
     wären
    0.56
     Would
    0.54
    Would
    0.53
     probably
    0.52
     wäre
    0.52
    łby
    0.52
     würde
    0.51
     WOULD
    0.50
    Activations Density 0.316%

    No Known Activations