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. 15-GEMMASCOPE-RES-16K
    6. 2728
    Prev
    Next
    INDEX
    Explanations

    assertions and error handling statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bewerken
    -0.71
    UserScript
    -0.65
    IBOutlet
    -0.63
    íncia
    -0.62
    __]
    -0.58
    colo
    -0.54
    IVO
    -0.54
     personal
    -0.54
    DispatchToProps
    -0.53
     *((
    -0.53
    POSITIVE LOGITS
    checkNotNull
    0.70
     propTypes
    0.59
     disponibilités
    0.59
    requireNonNull
    0.59
     NUKAT
    0.58
    assert
    0.57
     sanity
    0.56
    Preconditions
    0.56
    IntoConstraints
    0.56
     Sanity
    0.56
    Activations Density 0.105%

    No Known Activations