© 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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 31329
    Prev
    Next
    INDEX
    Explanations

    references to specific types of biological substances or methodologies

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

    biotin or bio-related terms

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     OMITBAD
    -0.69
     disambiguazione
    -0.63
     parachoque
    -0.54
     cuentos
    -0.52
    careous
    -0.52
     kracht
    -0.52
     Савезне
    -0.50
     traditionnelle
    -0.50
     bezeichneter
    -0.50
     armée
    -0.50
    POSITIVE LOGITS
     biome
    1.13
     Bio
    1.08
     bio
    1.06
    Biome
    1.05
    Bio
    0.98
    bio
    0.95
     biotin
    0.93
     BIO
    0.84
    BIO
    0.78
     bios
    0.74
    Activations Density 0.022%

    No Known Activations