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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 108009
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns and names related to products or brands

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

    thing-o-matic

    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
     resourceCulture
    -0.54
    Personensuche
    -0.51
    MLLoader
    -0.48
    Xna
    -0.45
    GEBURTSDATUM
    -0.44
    angliski
    -0.43
     contextLoads
    -0.43
    rungsseite
    -0.42
    #+#
    -0.41
    AddTagHelper
    -0.41
    POSITIVE LOGITS
     Speedy
    0.46
     EZ
    0.42
    rifty
    0.42
    Handy
    0.41
    êmios
    0.41
     Patio
    0.41
     Manor
    0.41
     Beneficial
    0.40
    便利な
    0.40
    EZ
    0.40
    Activations Density 0.112%

    No Known Activations