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. 5-GEMMASCOPE-RES-16K
    6. 1777
    Prev
    Next
    INDEX
    Explanations

    references to companies and organizations along with their locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.66
     rapides
    -0.45
    Geplaatst
    -0.45
     spéciales
    -0.44
    cómo
    -0.44
    İstinadlar
    -0.43
     resultCode
    -0.43
    HasForeignKey
    -0.43
    FINALLY
    -0.43
     gradova
    -0.42
    POSITIVE LOGITS
     based
    0.86
    based
    0.85
    quartered
    0.83
     BASED
    0.79
     headquartered
    0.75
     multinational
    0.74
    BASED
    0.73
     HasFactory
    0.73
    Based
    0.70
     Olsson
    0.69
    Activations Density 0.184%

    No Known Activations