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. 74
    Prev
    Next
    INDEX
    Explanations

    academic concepts and theories related to social sciences

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

    academic or research-related terminology and concepts.

    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
    ativement
    -0.47
     wireType
    -0.46
    Rujuakan
    -0.46
     utafitiHapana
    -0.45
    InvalidProtocol
    -0.45
    StoryboardSegue
    -0.44
    Caratter
    -0.44
     same
    -0.41
    ResponseWriter
    -0.41
     Taktlose
    -0.41
    POSITIVE LOGITS
     theory
    0.63
     Theory
    0.56
     Theorie
    0.55
     theories
    0.51
     principles
    0.51
     concept
    0.50
    Theory
    0.49
    DataAnnotations
    0.48
    theory
    0.48
     concepts
    0.47
    Activations Density 0.239%

    No Known Activations