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. 22-GEMMASCOPE-RES-16K
    6. 8035
    Prev
    Next
    INDEX
    Explanations

    Java programming constructs related to Spring framework configurations and annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets and annotations

    np_acts-logits-general · gemini-2.0-flash

    Springfox, Enable, dependency, Bean

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteBehavior
    -0.66
    LayoutStyle
    -0.48
    OrBuilder
    -0.48
    WithEmail
    -0.47
    .$,
    -0.46
     Ud
    -0.43
    sizeCache
    -0.42
     crash
    -0.42
    fillType
    -0.42
     crashes
    -0.41
    POSITIVE LOGITS
    قایناق‌لار
    0.62
    ⓧ
    0.62
     esboço
    0.59
    Spel
    0.58
    perties
    0.58
     fondament
    0.58
     متعلقه
    0.57
    erequisites
    0.57
    chuck
    0.56
     Spisak
    0.55
    Activations Density 0.136%

    No Known Activations