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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53081
    Prev
    Next
    INDEX
    Explanations

    technical terms related to machinery and its components

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

    past tense verbs 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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     pleaſure
    -0.74
     Majefty
    -0.74
     Jefus
    -0.72
     doubtnut
    -0.71
     Monfieur
    -0.69
     poffible
    -0.68
    SequentialGroup
    -0.68
     Diretto
    -0.67
    TagMode
    -0.67
     Diſ
    -0.67
    POSITIVE LOGITS
     use
    0.64
     
    0.53
     using
    0.50
     color
    0.49
     Use
    0.49
     h
    0.47
     cover
    0.46
    eiro
    0.45
     frequently
    0.45
     lei
    0.44
    Activations Density 1.615%

    No Known Activations