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. 10-GEMMASCOPE-RES-16K
    6. 12532
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or conjecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    al
    -0.75
    -
    -0.74
     wings
    -0.70
     girls
    -0.69
     break
    -0.68
    плек
    -0.67
     Seb
    -0.67
    t
    -0.65
     boys
    -0.65
    bre
    -0.64
    POSITIVE LOGITS
    Datuak
    0.98
    theless
    0.95
    faßt
    0.94
     utilizing
    0.92
     ainfi
    0.89
    どく
    0.88
     utilising
    0.88
    Bliss
    0.88
    unately
    0.87
    Portail
    0.87
    Activations Density 0.207%

    No Known Activations