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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 2579
    Prev
    Next
    INDEX
    Explanations

    relational conditions involving length, size, or counts in data structures

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

    Conditions with comparisons based on length or size

    np_acts-logits-general · gemini-2.0-flash

    length checks

    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
    bootstrapcdn
    -0.83
    MigrationBuilder
    -0.81
    Билгалдахарш
    -0.80
    nodoc
    -0.78
    دانشنامهٔ
    -0.75
     חיצוניים
    -0.73
    windowFixed
    -0.72
     @"/
    -0.72
     صوتيه
    -0.71
    richTextPanel
    -0.70
    POSITIVE LOGITS
     >
    0.77
     greater
    0.69
     exceeds
    0.68
    >
    0.64
     exceeded
    0.60
     >=
    0.58
    greater
    0.57
     sufficient
    0.55
     exceed
    0.54
     exceeding
    0.54
    Activations Density 0.125%

    No Known Activations