Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-GEMMASCOPE-RES-16K
    6. 6191
    Prev
    Next
    INDEX
    Explanations

    code elements related to the manipulation and decoding of data structures in the Protobuf framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WindowConstants
    -0.63
    WaitGroup
    -0.61
    >>();
    -0.58
    >--}}
    -0.53
    >`;
    -0.51
     eventdata
    -0.51
    .*")]
    -0.50
    pédie
    -0.49
    tvguidetime
    -0.48
    Personensuche
    -0.48
    POSITIVE LOGITS
    StoryboardSegue
    0.99
    MLLoader
    0.76
    twimg
    0.72
    :][
    0.63
    FromJson
    0.59
    PROTOBUF
    0.59
    OuterClass
    0.58
    PageRoute
    0.57
     "..\..\
    0.56
    jspx
    0.56
    Activations Density 0.524%

    No Known Activations