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. 19-GEMMASCOPE-RES-16K
    6. 2005
    Prev
    Next
    INDEX
    Explanations

    technical details and specifications related to mechanical systems and their performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    griffen
    -0.63
    SerializedName
    -0.48
    hdys
    -0.48
     tärke
    -0.48
    antino
    -0.47
    ItemSelected
    -0.46
    extAlignment
    -0.46
    htiö
    -0.45
    digitalWrite
    -0.45
    مراجع
    -0.44
    POSITIVE LOGITS
     capacity
    2.57
     capability
    2.50
     capabilities
    2.43
     capacities
    2.27
     Capacity
    2.24
    capacity
    2.14
     Capabilities
    2.13
     Capability
    2.09
    Capacity
    2.07
     ability
    2.02
    Activations Density 0.428%

    No Known Activations