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. 19-GEMMASCOPE-RES-16K
    6. 1682
    Prev
    Next
    INDEX
    Explanations

    information relating to financial statistics and significant data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Unnamed
    -0.59
    turned
    -0.52
     dolu
    -0.51
    ISTIC
    -0.51
    acetate
    -0.49
    نات
    -0.48
    nerf
    -0.48
    curacy
    -0.48
    ETERS
    -0.47
    ený
    -0.46
    POSITIVE LOGITS
     kasarigan
    0.75
    DoubleQuotes
    0.67
     Roskov
    0.61
     propOrder
    0.60
    AddHtmlAttribute
    0.59
     calendriers
    0.55
     MonoBehaviour
    0.55
    webElement
    0.54
     [*]
    0.54
    IntoConstraints
    0.54
    Activations Density 0.416%

    No Known Activations