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. 6345
    Prev
    Next
    INDEX
    Explanations

    commands or queries related to searching or locating information

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

    "find" or "found"

    np_acts-logits-general · gemini-2.0-flash

    finding or being found

    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
     torr
    -0.67
     photolibrary
    -0.66
    httphttps
    -0.66
    DataOutputStream
    -0.66
    yesha
    -0.66
     McIl
    -0.65
     matel
    -0.65
     Cæsar
    -0.64
    MathML
    -0.63
     Cochin
    -0.63
    POSITIVE LOGITS
     FIND
    1.44
    FIND
    1.34
     Finds
    1.25
    find
    1.21
     finds
    1.18
     find
    1.17
     Find
    1.14
    Find
    1.12
    finds
    1.07
     Findlay
    1.06
    Activations Density 0.144%

    No Known Activations