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. 17-GEMMASCOPE-RES-16K
    6. 7144
    Prev
    Next
    INDEX
    Explanations

    references to different types of flooring and their conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    повід
    -0.60
     kans
    -0.53
     sauvage
    -0.52
    krom
    -0.51
     nature
    -0.51
    matitis
    -0.50
    cías
    -0.49
    ivant
    -0.49
    geben
    -0.49
    ../../
    -0.48
    POSITIVE LOGITS
     Floor
    1.05
    GraphicsUnit
    1.03
     Floors
    1.02
    floor
    1.02
    FLOOR
    0.99
     FLOOR
    0.97
    floors
    0.95
     floors
    0.94
    Floor
    0.94
     floor
    0.93
    Activations Density 0.205%

    No Known Activations