© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10311
    Prev
    Next
    INDEX
    Explanations

    references to various species and their classifications

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

    biological "species"

    np_acts-logits-general · gemini-2.0-flash

    biological species

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
    曖昧さ回避
    -0.53
    дравству
    -0.51
     المعيارى
    -0.48
    tagHelperRunner
    -0.46
     vielen
    -0.46
    Help
    -0.45
     Tilt
    -0.44
    boven
    -0.44
     Help
    -0.43
    talk
    -0.43
    POSITIVE LOGITS
     species
    2.00
     Species
    1.87
    Species
    1.86
    species
    1.82
     SPECIES
    1.66
    pecies
    1.58
    SPECIES
    1.52
     especies
    1.37
     specie
    1.37
     espécies
    1.18
    Activations Density 0.185%

    No Known Activations