© 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. 3677
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to various conditions or requirements

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

    "condition" followed by different words

    np_acts-logits-general · gemini-2.0-flash

    condition followed by defining words

    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
    揄
    -0.65
    🏻
    -0.64
     AppColors
    -0.59
    SwingConstants
    -0.58
     useCallback
    -0.57
     directos
    -0.56
    crollView
    -0.56
    ulgação
    -0.55
    élien
    -0.54
    ssaint
    -0.53
    POSITIVE LOGITS
     conditions
    1.00
     Conditions
    0.99
    Conditions
    0.95
    conditions
    0.93
     CONDITIONS
    0.84
    الإنجليزية
    0.74
    反射
    0.72
    Condition
    0.70
     Condition
    0.70
    Condi
    0.68
    Activations Density 0.101%

    No Known Activations