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. 2-GEMMASCOPE-RES-16K
    6. 6293
    Prev
    Next
    INDEX
    Explanations

    occurrences of syntax and characters related to programming, specifically in the context of PHP

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.72
     "
    -0.56
    ato
    -0.56
     Moly
    -0.55
     (
    -0.53
    NotBe
    -0.51
    amor
    -0.50
     '
    -0.50
     Barr
    -0.48
     Level
    -0.48
    POSITIVE LOGITS
    [$
    1.70
    '][$
    1.38
    ="<?=$
    1.36
    <?=$
    1.35
    =$
    1.28
    ">'.$
    1.22
    ][$
    1.21
    +$
    1.20
    --$
    1.19
     {$
    1.18
    Activations Density 0.277%

    No Known Activations