© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 421
    Prev
    Next
    INDEX
    Explanations

    terms related to marine biology and sponge species

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

    technical and scientific terminology related to marine sponge research and silica chemistry.

    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
    findpost
    -0.43
     iconLine
    -0.41
     AssemblyCulture
    -0.40
    τως
    -0.36
    Билгалдахарш
    -0.35
    สู
    -0.35
    鱷
    -0.35
    鳄
    -0.35
    ArgsConstructor
    -0.35
     CreateTagHelper
    -0.34
    POSITIVE LOGITS
     polyps
    0.85
     corals
    0.81
     tentacles
    0.77
     coral
    0.72
     jellyfish
    0.67
     Tenta
    0.67
     polyp
    0.66
     tenta
    0.65
    coral
    0.63
     octopus
    0.63
    Activations Density 0.315%

    No Known Activations