© 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-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 5831
    Prev
    Next
    INDEX
    Explanations

    PHP opening and closing tags and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -0.52
     Fall
    -0.49
     Dillon
    -0.47
    ,
    -0.47
     Cline
    -0.46
    </em>
    -0.46
     Oliva
    -0.46
    ⓘ
    -0.45
    )-
    -0.44
     establishment
    -0.43
    POSITIVE LOGITS
    <?
    1.59
     '<?
    1.38
    ="<?
    1.31
     <?
    1.30
     "<?
    1.20
    <?
    1.16
    ><?
    1.09
    "><?
    1.05
    =<?
    0.99
    <?
    0.85
    Activations Density 0.159%

    No Known Activations