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. 25-GEMMASCOPE-RES-16K
    6. 10403
    Prev
    Next
    INDEX
    Explanations

    negations and phrases related to uncertainty or inability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lakhs
    -0.56
    ukunfts
    -0.47
    ęgn
    -0.46
    crumbs
    -0.45
    cepter
    -0.44
     lotus
    -0.44
     of
    -0.43
    quoise
    -0.43
     your
    -0.43
     you
    -0.42
    POSITIVE LOGITS
    ことも
    0.82
    ことが
    0.82
    ことで
    0.79
    ことに
    0.79
    のが
    0.78
    ことは
    0.77
    ことを
    0.76
    ことから
    0.74
    こともある
    0.74
    ことがある
    0.72
    Activations Density 0.069%

    No Known Activations