Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 13393
    Prev
    Next
    INDEX
    Explanations

    references to individuals who have established or created organizations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oilers
    -0.72
    boldsymbol
    -0.70
    jewództ
    -0.66
     utafitiHapana
    -0.63
    Mediabestanden
    -0.62
    soort
    -0.61
     Alsace
    -0.61
     الرياضيه
    -0.60
     Recife
    -0.59
    Especies
    -0.58
    POSITIVE LOGITS
     founded
    1.78
     founding
    1.70
     founders
    1.64
     founder
    1.61
    founders
    1.60
    founder
    1.53
     Founders
    1.51
     Founded
    1.50
     Founder
    1.49
     fundador
    1.46
    Activations Density 0.058%

    No Known Activations