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. 408
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a specific intention or aim in various contexts

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

    the word "purpose" and phrases detailing the purpose of a study or document.

    oai_token-act-pair · gpt-4oTriggered 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
    afficheront
    -0.93
     dalamnya
    -0.91
    انتهای
    -0.88
    zzarella
    -0.86
    IsMutable
    -0.85
    orianCalendar
    -0.84
     ingrat
    -0.84
     HasFactory
    -0.84
     endblock
    -0.82
     GenerationType
    -0.80
    POSITIVE LOGITS
     Purpose
    1.52
     purposes
    1.50
     purpose
    1.44
    Purpose
    1.42
    PURPOSE
    1.40
     PURPOSE
    1.37
    purpose
    1.26
     Purposes
    1.25
    purposes
    0.97
     propósitos
    0.91
    Activations Density 0.073%

    No Known Activations