Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 11171
    Prev
    Next
    INDEX
    Explanations

    expressions related to comfort and enjoyment in various contexts

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

    Describing something as "perfect" or "great"

    np_acts-logits-general · gemini-2.0-flash

    comfort and suitability

    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
    DrawerToggle
    -0.61
    StackNavigator
    -0.59
    ]--;
    -0.54
    Std
    -0.50
    😑
    -0.50
    😦
    -0.49
     strictement
    -0.48
     Worse
    -0.48
    😐
    -0.47
    😞
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.77
     geeignet
    0.74
     zeker
    0.73
     anytime
    0.71
     whether
    0.71
     especially
    0.69
     Whether
    0.69
    especially
    0.67
    Özel
    0.67
     alike
    0.67
    Activations Density 0.122%

    No Known Activations