© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 14459
    Prev
    Next
    INDEX
    Explanations

    numbers or numerical 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
    GEBURTSDATUM
    -1.24
    adpleegd
    -1.21
     ―――――
    -1.18
     propOrder
    -1.14
    protoimpl
    -1.14
    دانشنامهٔ
    -1.09
    AsUp
    -1.08
     ivelany
    -1.07
    хьтан
    -1.06
    Personensuche
    -1.05
    POSITIVE LOGITS
    mathrm
    0.98
    ’
    0.84
    '
    0.81
     
    0.74
    setcounter
    0.74
    2
    0.73
    <em>
    0.65
     The
    0.62
     I
    0.61
     shouldn
    0.61
    Activations Density 0.204%

    No Known Activations