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. 5072
    Prev
    Next
    INDEX
    Explanations

    discussions about future expectations and planning

    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
     set
    -0.45
    Finally
    -0.40
     k
    -0.40
    ↵
    -0.40
    dam
    -0.39
     K
    -0.39
     X
    -0.38
     basse
    -0.38
     Finally
    -0.38
    E
    -0.37
    POSITIVE LOGITS
     future
    2.16
    future
    1.95
     zukünf
    1.67
     upcoming
    1.67
    Future
    1.65
     künf
    1.61
     futuros
    1.61
    FUTURE
    1.55
    avenir
    1.53
     FUTURE
    1.52
    Activations Density 0.376%

    No Known Activations