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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31059
    Prev
    Next
    INDEX
    Explanations

    the presence of specific formatting or sections in a document, particularly the beginning markers of text segments

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

    `ium]` or `computing]{`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ."));
    -0.86
    ."]
    -0.85
    .")]
    -0.84
    "");
    -0.84
    !")
    -0.84
    ')]
    -0.81
    ."),
    -0.79
    ).
    -0.79
    "]]
    -0.78
    .";
    -0.78
    POSITIVE LOGITS
     I
    0.63
     if
    0.62
     yes
    0.58
     If
    0.57
    I
    0.56
     yeah
    0.55
    ,
    0.54
     Yes
    0.54
    If
    0.53
    Yes
    0.52
    Activations Density 0.078%

    No Known Activations