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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4784
    Prev
    Next
    INDEX
    Explanations

    elements of scientific or technical descriptions related to the assembly and function of devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BufferException
    -0.73
    WebVitals
    -0.64
     utafitiHapana
    -0.60
    TagMode
    -0.56
    <eos>
    -0.52
    TargetException
    -0.50
    apunov
    -0.48
    AddTagHelper
    -0.47
    ContentAsync
    -0.46
     المعيارى
    -0.45
    POSITIVE LOGITS
    PreferredItem
    0.70
    DockStyle
    0.63
    IsPostBack
    0.59
    Expedia
    0.57
    RTDA
    0.55
    الدراسه
    0.55
     setempat
    0.55
    ⓧ
    0.53
    "]];
    0.52
     Ubicación
    0.52
    Activations Density 15.454%

    No Known Activations