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. 13861
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures and key-value pair processing in programming

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

    "key" or its variations

    np_acts-logits-general · gemini-2.0-flash

    key and keys

    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
    dorp
    -0.57
    unov
    -0.51
    yot
    -0.50
     Beres
    -0.48
    onias
    -0.47
    getDoctrine
    -0.47
    gani
    -0.46
    ourced
    -0.46
    dende
    -0.46
     INSTANCE
    -0.46
    POSITIVE LOGITS
     key
    2.51
    key
    2.32
     keys
    2.28
     Key
    2.21
    Key
    2.19
     KEY
    2.10
    KEY
    2.03
     Keys
    1.92
    keys
    1.90
    Keys
    1.79
    Activations Density 0.245%

    No Known Activations