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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2118
    Prev
    Next
    INDEX
    Explanations

    information related to mating systems and reproductive behaviors

    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
    RectangleBorder
    -0.67
    ChildScrollView
    -0.63
     ExecuteAsync
    -0.54
    othelial
    -0.54
    SqlDataReader
    -0.53
     становника
    -0.53
    oblastoma
    -0.53
    gebnissen
    -0.52
     متعلقه
    -0.52
     Finger
    -0.52
    POSITIVE LOGITS
     mating
    0.86
     females
    0.82
     Females
    0.78
    Females
    0.74
     hembra
    0.68
     female
    0.68
     males
    0.67
     predators
    0.66
     territ
    0.66
     territorial
    0.66
    Activations Density 0.490%

    No Known Activations