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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109772
    Prev
    Next
    INDEX
    Explanations

    instances of competition or combat-related activities and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scrimmage
    -0.66
     scrum
    -0.49
     scrim
    -0.49
     noqa
    -0.47
    Cyfarwyddwr
    -0.45
    хьтан
    -0.44
    цездатний
    -0.44
    __*/
    -0.44
     Autorizaciones
    -0.42
    IsMutable
    -0.40
    POSITIVE LOGITS
    stdc
    0.40
    demand
    0.40
     Palestina
    0.40
    FAQ
    0.38
    flow
    0.38
    Geplaatst
    0.38
    extAlignment
    0.38
     vrijwilli
    0.38
     Trennung
    0.38
    operability
    0.37
    Activations Density 0.006%

    No Known Activations