© 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. 22-GEMMASCOPE-RES-16K
    11. 13286
    Prev
    Next
    INDEX
    Explanations

    roles and titles associated with political or corporate contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Titles or roles people hold

    np_acts-logits-general · gemini-2.0-flash

    title and name said

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.50
    text
    -0.44
     U
    -0.42
     The
    -0.42
     text
    -0.42
    เภ
    -0.42
    寡
    -0.41
    2
    -0.41
     Text
    -0.40
    ngua
    -0.39
    POSITIVE LOGITS
    Personendaten
    0.93
    Personensuche
    0.91
    makeConstraints
    0.88
     calendriers
    0.85
    fjspx
    0.84
     referenties
    0.83
    AccessorTable
    0.81
    HasAnnotation
    0.80
     autorytatywna
    0.78
    SourceChecksum
    0.78
    Activations Density 0.128%

    No Known Activations