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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 655
    Prev
    Next
    INDEX
    Explanations

    phrases related to raising awareness or concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.86
     CURIAM
    -0.82
    onov
    -0.72
    ürtel
    -0.72
     AssemblyCulture
    -0.69
     Lehmann
    -0.66
    aughan
    -0.66
    inoco
    -0.66
    continent
    -0.65
    hastly
    -0.65
    POSITIVE LOGITS
     raise
    2.46
     Raise
    2.40
     raised
    2.39
     raising
    2.35
     raises
    2.30
     Raising
    2.26
    Raise
    2.26
    raised
    2.24
    raise
    2.23
     Raised
    2.16
    Activations Density 0.061%

    No Known Activations