© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9078
    Prev
    Next
    INDEX
    Explanations

    reference tags related to paragraphs and links within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.97
    endphp
    -0.88
    下载附件
    -0.82
     }}$}
    -0.80
    "]);
    -0.77
     protoimpl
    -0.76
    ")));
    -0.75
     endblock
    -0.75
    )";
    -0.75
     PeEnEo
    -0.74
    POSITIVE LOGITS
     "
    0.49
    ("
    0.47
    ["
    0.46
     “
    0.45
    <i>
    0.42
    “
    0.40
    ['
    0.38
    <em>
    0.38
     razonable
    0.38
    <td>
    0.37
    Activations Density 0.189%

    No Known Activations