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. 18-GEMMASCOPE-RES-16K
    6. 14525
    Prev
    Next
    INDEX
    Explanations

    structures related to mathematical or physical modeling

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

    Values with exponents and multiplication

    np_acts-logits-general · gemini-2.0-flash

    mass and astronomical units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.52
    UnknownFieldSet
    -0.49
    AnimationsModule
    -0.48
    StoryboardSegue
    -0.47
    +};
    -0.46
    حوالہ
    -0.46
    ContextHolder
    -0.46
    NewReader
    -0.46
     Product
    -0.45
    তথ্যসূত্র
    -0.45
    POSITIVE LOGITS
    TagMode
    0.72
     autorytatywna
    0.68
    المناصب
    0.65
    المكان
    0.56
     mass
    0.55
    WebElementEntity
    0.55
    DeleteBehavior
    0.55
    SOLID
    0.54
    rungsseite
    0.54
    Solid
    0.54
    Activations Density 0.404%

    No Known Activations