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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 2972
    Prev
    Next
    INDEX
    Explanations

    numeric sequences and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onAttach
    -0.80
    writeField
    -0.78
    InjectAttribute
    -0.76
    +#+#
    -0.73
    basicConfig
    -0.72
    RetentionPolicy
    -0.72
    SharedDtor
    -0.69
    GEBURTSDATUM
    -0.69
     Pompey
    -0.68
    Autoritní
    -0.66
    POSITIVE LOGITS
    rač
    0.53
    simus
    0.52
     foglal
    0.51
     دیکھیے
    0.50
    bate
    0.46
    мс
    0.46
     hlavní
    0.45
     Main
    0.45
     Audiodateien
    0.44
    URY
    0.44
    Activations Density 1.146%

    No Known Activations