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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-131K
    6. 38902
    Prev
    Next
    INDEX
    Explanations

    relationships and actions related to obligations and responsibilities in legal or contractual contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.60
    AndroidJUnit
    -0.55
    featureID
    -0.55
     AssemblyVersion
    -0.52
    bleshooting
    -0.48
     betweenstory
    -0.48
    nium
    -0.48
    ervlak
    -0.47
    orship
    -0.47
    ksk
    -0.46
    POSITIVE LOGITS
     tartalomajánló
    0.40
     kommunen
    0.37
     hydrauli
    0.35
     Recursos
    0.34
    BagConstraints
    0.33
     utilisateur
    0.32
    (!__
    0.32
     obě
    0.30
    isRequired
    0.30
     humaine
    0.30
    Activations Density 0.066%

    No Known Activations