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. 3371
    Prev
    Next
    INDEX
    Explanations

    references to specific vehicle models and their features

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

    Luxury car brands/models

    np_acts-logits-general · gemini-2.0-flash

    automotive brands and models

    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
    RenderAtEndOf
    -0.65
    TypedDataSet
    -0.61
    ChildScrollView
    -0.59
     arşivlendi
    -0.55
     <>",
    -0.55
     Goul
    -0.51
    wsze
    -0.51
     Fukushima
    -0.50
    Itoa
    -0.49
    StoryboardSegue
    -0.49
    POSITIVE LOGITS
     Cull
    0.66
     SUV
    0.65
    AMG
    0.63
     luxury
    0.59
    tvguidetime
    0.59
    SUV
    0.58
     AMG
    0.57
     amg
    0.56
     GLE
    0.55
     SUVs
    0.53
    Activations Density 0.155%

    No Known Activations