Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 6666
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of casting and related processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TestBed
    -0.54
     уве
    -0.53
     chi̍t
    -0.52
     Krum
    -0.49
    BufferException
    -0.49
    towym
    -0.48
     Chalmers
    -0.48
    isseurs
    -0.47
     واج
    -0.47
     useStyles
    -0.46
    POSITIVE LOGITS
    ру
    0.90
    го
    0.82
     kasarigan
    0.77
     NSCoder
    0.73
    Cast
    0.69
     ru
    0.68
    énario
    0.66
    ru
    0.64
    rungsseite
    0.63
    Hozzáférés
    0.63
    Activations Density 0.133%

    No Known Activations