© 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. 8112
    Prev
    Next
    INDEX
    Explanations

    legal responsibilities and duties related to succession and property rights

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

    Responsibility/burden is placed or rests

    np_acts-logits-general · gemini-2.0-flash

    responsibility and belonging

    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
    ظمة
    -0.52
     liné
    -0.47
    setVisible
    -0.45
     specchio
    -0.44
     își
    -0.43
    onViewCreated
    -0.43
    archiviato
    -0.43
     linear
    -0.42
    脚注の使い方
    -0.42
    ENABLED
    -0.42
    POSITIVE LOGITS
     belongs
    1.66
     belong
    1.60
     belonged
    1.53
    belong
    1.46
    belongs
    1.40
     belonging
    1.19
     appartient
    1.13
     Belong
    1.06
     pertence
    1.03
     apparti
    0.95
    Activations Density 0.371%

    No Known Activations