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. 12-GEMMASCOPE-RES-16K
    6. 2650
    Prev
    Next
    INDEX
    Explanations

    references to the future and positive developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tryk
    -0.47
    mayın
    -0.46
     Harding
    -0.45
     rơi
    -0.44
    REGULAR
    -0.44
    組
    -0.44
     regular
    -0.44
    ByType
    -0.44
     pauvres
    -0.44
    illa
    -0.43
    POSITIVE LOGITS
     future
    1.13
    future
    1.10
     toekomst
    1.02
    Future
    0.99
    avenir
    0.98
     Zukunft
    0.90
    FUTURE
    0.90
     Future
    0.89
     avenir
    0.89
     FUTURE
    0.89
    Activations Density 0.206%

    No Known Activations