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-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 14257
    Prev
    Next
    INDEX
    Explanations

    terms related to consulting and advice-giving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Elden
    -0.79
     Jof
    -0.75
     HomeComponent
    -0.74
    +#+#
    -0.72
    çalves
    -0.72
     Ys
    -0.72
    ENTITY
    -0.70
     Morde
    -0.70
    வர
    -0.70
     Dov
    -0.70
    POSITIVE LOGITS
     consult
    1.22
     CONSULT
    1.21
     Consult
    1.14
     consulting
    1.13
    CONSULT
    1.12
     consultation
    1.11
    consult
    1.11
    Consult
    1.09
     consulted
    1.02
     consultant
    0.99
    Activations Density 0.099%

    No Known Activations