© 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. 22-GEMMASCOPE-RES-16K
    6. 11417
    Prev
    Next
    INDEX
    Explanations

    discussions about the ideals and principles of marriage

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

    preceding positive adjectives

    np_acts-logits-general · gemini-2.0-flash

    marriage commitment stability

    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
    warf
    -0.48
     ansatte
    -0.48
    DaoImpl
    -0.47
    Greetings
    -0.46
     客
    -0.46
    客
    -0.44
    Cousin
    -0.43
     visitor
    -0.43
    นะนำ
    -0.42
     pecados
    -0.41
    POSITIVE LOGITS
     monog
    0.94
     unconditional
    0.84
     commitment
    0.82
     stability
    0.77
     loyalty
    0.76
     loving
    0.74
    Hochspringen
    0.74
     AssemblyProduct
    0.72
     stabilité
    0.72
     Commitment
    0.71
    Activations Density 0.262%

    No Known Activations