© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 10637
    Prev
    Next
    INDEX
    Explanations

    occurrences of significant numeric values and markers in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.88
    SOUNDBITE
    -0.56
    ಃ
    -0.55
    featureID
    -0.53
    ansa
    -0.51
    \}=\
    -0.50
     ErrIntOverflow
    -0.50
    ien
    -0.49
    asi
    -0.49
    igu
    -0.49
    POSITIVE LOGITS
    <bos>
    1.90
    ’
    1.65
    '
    1.59
    begin
    1.22
    €™
    0.81
    CloseOperation
    0.78
    setcounter
    0.76
    bbene
    0.76
     виправивши
    0.74
    évaluateur
    0.73
    Activations Density 0.465%

    No Known Activations