© 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. 20-GEMMASCOPE-RES-16K
    6. 8432
    Prev
    Next
    INDEX
    Explanations

    elements related to roofing materials and their attributes

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

    Describing surface textures or patterns

    np_acts-logits-general · gemini-2.0-flash

    smooth, rough surfaces, texture, pores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.79
    IntoConstraints
    -0.77
     pleaſure
    -0.77
     myſelf
    -0.77
     initComponents
    -0.76
     Monfieur
    -0.72
     houſe
    -0.71
     purpoſe
    -0.69
     laſt
    -0.69
    Personendaten
    -0.69
    POSITIVE LOGITS
     pattern
    1.04
     patterns
    0.93
    pattern
    0.90
     texture
    0.87
     Pattern
    0.81
     PATTERN
    0.81
     grooves
    0.77
     grain
    0.74
    patterns
    0.74
    PATTERN
    0.73
    Activations Density 0.784%

    No Known Activations