© 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. 18-GEMMASCOPE-RES-16K
    11. 1765
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal responsibility and the concept of choice

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

    Follows a word related to responsibility or obligation

    np_acts-logits-general · gemini-2.0-flash

    responsibility and obligation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.61
    Personendaten
    -0.51
    IntoConstraints
    -0.51
     okuyayım
    -0.51
    hots
    -0.49
     Waray
    -0.48
    ஈ
    -0.47
    iorno
    -0.46
    AutoScaleMode
    -0.44
    WillAppear
    -0.44
    POSITIVE LOGITS
     responsibility
    1.14
     onus
    1.08
    responsibility
    1.02
     responsabilidad
    0.92
    Responsibility
    0.90
     Responsibility
    0.89
     responsabilità
    0.85
     up
    0.84
     burden
    0.71
     responsabilité
    0.71
    Activations Density 0.210%

    No Known Activations