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. 16-GEMMASCOPE-RES-16K
    6. 6088
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons or examples

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

    Follows prepositions "with," "about," "at," or "for."

    np_acts-logits-general · gemini-2.0-flash

    prepositions followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.83
    SequentialGroup
    -0.81
    MigrationBuilder
    -0.79
    imageshack
    -0.78
    mybatisplus
    -0.78
    WithIOException
    -0.76
     Sarm
    -0.75
    Personensuche
    -0.72
    typeorm
    -0.70
    ThroughAttribute
    -0.70
    POSITIVE LOGITS
     the
    1.02
     our
    0.86
     those
    0.67
     بالنسبة
    0.65
     when
    0.60
     me
    0.57
     my
    0.57
     some
    0.56
     your
    0.54
    :
    0.53
    Activations Density 0.353%

    No Known Activations