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. 8036
    Prev
    Next
    INDEX
    Explanations

    CSS properties related to layout and spacing

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

    "px", units of measure for web design

    np_acts-logits-general · gemini-2.0-flash

    CSS pixel units

    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
    Tracce
    -0.67
    mesis
    -0.59
    ngdoc
    -0.56
    ?}",
    -0.56
    __]
    -0.53
    [...,
    -0.53
    |
    
    -0.53
     muualla
    -0.53
     Temperatur
    -0.52
     ke
    -0.51
    POSITIVE LOGITS
    px
    1.16
    PX
    0.79
     ſeveral
    0.77
    em
    0.76
     pleaſure
    0.70
     px
    0.70
     myſelf
    0.70
    Px
    0.69
     fevere
    0.69
    pt
    0.69
    Activations Density 0.173%

    No Known Activations