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. 21-GEMMASCOPE-RES-16K
    6. 15147
    Prev
    Next
    INDEX
    Explanations

    specific technical descriptions related to automotive engine components and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HomeAsUpEnabled
    -0.52
    titleMargin
    -0.48
    </tfoot>
    -0.48
    mampuan
    -0.48
    Skocz
    -0.48
     doInBackground
    -0.47
    oxane
    -0.46
    outState
    -0.46
    SOUNDBITE
    -0.45
    sula
    -0.45
    POSITIVE LOGITS
     cam
    0.81
     cams
    0.65
    GeneratedMessage
    0.64
     Cam
    0.61
     timing
    0.61
    cam
    0.59
    ArgsConstructor
    0.58
    yntaxException
    0.57
    Cam
    0.56
    GroupLayout
    0.56
    Activations Density 0.127%

    No Known Activations