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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 1266
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ownership or association

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

    First letters of words

    np_acts-logits-general · gemini-2.0-flash

    reportedly begun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرخصة
    -0.32
     gratuita
    -0.32
     métiers
    -0.30
     milk
    -0.29
     videa
    -0.28
    สุข
    -0.28
     boissons
    -0.28
     paš
    -0.28
     argint
    -0.28
     salg
    -0.27
    POSITIVE LOGITS
     surla
    0.73
     للاسماء
    0.71
     informée
    0.69
     betweenstory
    0.66
    transQ
    0.66
     Italijanski
    0.59
    ernalia
    0.59
     ProtoMessage
    0.58
     nakalista
    0.57
    NameInMap
    0.57
    Activations Density 0.283%

    No Known Activations