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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9333
    Prev
    Next
    INDEX
    Explanations

    system-related keywords and error messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.67
    rungsseite
    -0.64
    fhir
    -0.62
    contentLoaded
    -0.61
    GEBURTSDATUM
    -0.60
    تقاوى
    -0.59
     defaultstate
    -0.59
     ***!
    -0.59
    SourceChecksum
    -0.56
     SwitchCompat
    -0.56
    POSITIVE LOGITS
    ValueGeneration
    0.58
    CAPACITY
    0.55
     CAPACITY
    0.54
     space
    0.54
     capacity
    0.53
     Capacity
    0.51
     kapasitas
    0.50
    capacity
    0.49
     raya
    0.48
     spaces
    0.48
    Activations Density 0.293%

    No Known Activations