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. 12-GEMMASCOPE-RES-65K
    6. 36621
    Prev
    Next
    INDEX
    Explanations

    references to data retrieval and API operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.82
    <?
    -0.81
    Demografie
    -0.63
    chiha
    -0.62
    swire
    -0.62
    όμε
    -0.62
    Adverti
    -0.61
    CppMethod
    -0.60
    dasarkan
    -0.60
    corrhi
    -0.60
    POSITIVE LOGITS
     numerus
    0.66
     BoxDecoration
    0.61
    fetch
    0.59
    Caprio
    0.58
    ichord
    0.52
     araw
    0.52
     fetch
    0.52
    enderror
    0.51
     voeren
    0.51
    Vist
    0.50
    Activations Density 0.002%

    No Known Activations