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. 20-GEMMASCOPE-RES-16K
    6. 15480
    Prev
    Next
    INDEX
    Explanations

    financial figures and fiscal information related to time periods and performance

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

    Dates with separators

    np_acts-logits-general · gemini-2.0-flash

    coefficients of numbers or probabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    +#+#
    -0.68
    MemoryWarning
    -0.66
     Lightboxes
    -0.58
    MessageTagHelper
    -0.55
     للاسماء
    -0.55
    })));
    -0.54
    SharedDtor
    -0.53
    oredCriteria
    -0.52
     CanadaChoose
    -0.51
     pinulongan
    -0.50
    POSITIVE LOGITS
     Paglinawan
    0.66
    CDCl
    0.57
    Manbalar
    0.55
    NewUrlParser
    0.54
     utafitiHapana
    0.49
    early
    0.49
    сылкі
    0.47
    AnimationFrame
    0.47
    geving
    0.47
    ]='\
    0.46
    Activations Density 0.143%

    No Known Activations