© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 6787
    Prev
    Next
    INDEX
    Explanations

    syntax-related elements in programming code, such as brackets and parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    til
    -0.57
     (
    -0.55
    men
    -0.54
    ,
    -0.53
    es
    -0.53
    ti
    -0.52
     in
    -0.52
    ok
    -0.51
    ls
    -0.51
     at
    -0.50
    POSITIVE LOGITS
     الحره
    1.22
    !")
    1.14
    ])));
    1.14
    setVerticalGroup
    1.12
    ."],
    1.11
    .")]
    1.09
    InjectAttribute
    1.05
    ]));
    1.04
    TagMode
    1.04
    }\]
    1.03
    Activations Density 0.146%

    No Known Activations