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. 3-GEMMASCOPE-RES-16K
    6. 6108
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     planète
    -0.82
    Décès
    -0.73
    Переваги
    -0.73
     Kaufman
    -0.73
     vertes
    -0.72
     Walters
    -0.72
     tarko
    -0.71
    prefixer
    -0.71
    UVWXYZ
    -0.70
     Cáceres
    -0.70
    POSITIVE LOGITS
     seem
    2.40
     seems
    2.25
     seemed
    2.22
    seems
    2.10
    seem
    2.05
     Seems
    2.05
    Seems
    2.03
    seemed
    1.98
     Seem
    1.92
     seeming
    1.56
    Activations Density 0.040%

    No Known Activations