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. 6
    Prev
    Next
    INDEX
    Explanations

    terms related to honesty and transparency in communication with the voters

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

    phrases related to public disclosure or presentation.

    oai_token-act-pair · gpt-4oTriggered by @timna

    phrases that indicate an action or communication being directed toward a specific recipient or audience, typically introduced by a preposition marking the addressee.

    oai_token-act-pair · gpt-5Triggered by @timna
    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
    /%
    -0.46
     Baillargeon
    -0.45
    -%
    -0.43
     Individ
    -0.41
    ciclopedia
    -0.39
    yarnpkg
    -0.38
    Individ
    -0.38
    individ
    -0.38
     persoonlijke
    -0.37
     trovo
    -0.37
    POSITIVE LOGITS
     audiences
    1.10
     viewers
    0.98
     readers
    0.97
     audience
    0.89
    ########.
    0.88
    audience
    0.81
     voters
    0.81
     customers
    0.81
     fans
    0.81
     listeners
    0.80
    Activations Density 0.267%

    No Known Activations