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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2965
    Prev
    Next
    INDEX
    Explanations

    botanical terms related to plant species and their characteristics

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

    scientific and botanical descriptions of plants and their characteristics.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     թվական
    -0.49
    StoryboardSegue
    -0.46
     ſche
    -0.46
    phylococcus
    -0.44
     repaired
    -0.43
     jsonString
    -0.43
     eventType
    -0.42
     laſt
    -0.42
    complexContent
    -0.42
    postmedia
    -0.42
    POSITIVE LOGITS
     commonly
    0.63
     comunes
    0.62
     habitat
    0.57
     common
    0.57
     comuns
    0.55
     species
    0.54
     genus
    0.53
     Commonly
    0.52
    common
    0.52
     pows
    0.52
    Activations Density 0.499%

    No Known Activations