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. Residual Stream - 131k
    5. 23-GEMMASCOPE-RES-131K
    6. 23204
    Prev
    Next
    INDEX
    Explanations

    terms related to consultations or consulting in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getID
    -0.54
    idalgo
    -0.53
    enumi
    -0.52
     Mejía
    -0.52
     indietro
    -0.50
     Pingback
    -0.50
     américains
    -0.50
     américaine
    -0.49
     wrongfully
    -0.49
     vectorielles
    -0.49
    POSITIVE LOGITS
     consult
    0.96
     Consult
    0.88
     consultation
    0.84
    consult
    0.81
     consulting
    0.79
     Consultation
    0.79
    Consult
    0.79
     consultative
    0.77
     CONSULT
    0.77
     consulted
    0.77
    Activations Density 0.004%

    No Known Activations