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. 23-GEMMASCOPE-RES-16K
    6. 2520
    Prev
    Next
    INDEX
    Explanations

    content related to art and its evolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.63
    ftagPool
    -0.63
     فريبيس
    -0.63
    RenderAtEndOf
    -0.61
    Autoritní
    -0.59
     CanadaChoose
    -0.59
     utafitiHapana
    -0.59
     enfans
    -0.58
     queſta
    -0.58
     kaynağından
    -0.57
    POSITIVE LOGITS
     influential
    0.43
     stylistic
    0.41
     contemporaries
    0.39
     influenced
    0.38
     trends
    0.38
     popular
    0.38
    influenced
    0.38
     early
    0.37
     tendencia
    0.36
     trend
    0.36
    Activations Density 0.282%

    No Known Activations