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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10665
    Prev
    Next
    INDEX
    Explanations

    PHP opening tags and related syntax

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

    code snippets using PHP-style opening tags and related inline PHP markers embedded in HTML or text.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the opening tag of PHP code blocks (`<?php` or `<?`).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.71
    .
    -0.62
    -
    -0.61
     Martel
    -0.60
    </em>
    -0.59
    )
    -0.57
     in
    -0.56
    </strong>
    -0.56
     Lund
    -0.52
    ing
    -0.52
    POSITIVE LOGITS
     étoient
    0.94
     avoient
    0.85
     zijne
    0.84
     pouvoit
    0.84
     auroit
    0.82
    ="<?
    0.81
     ainfi
    0.81
     '<?
    0.81
     anún
    0.80
    >{@
    0.79
    Activations Density 0.197%

    No Known Activations