© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 3329
    Prev
    Next
    INDEX
    Explanations

    closing punctuation marks and ending statements in programmatic code

    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
     المعيارى
    -0.55
    plom
    -0.55
     of
    -0.54
    atimes
    -0.54
     HAL
    -0.53
    bran
    -0.53
     bờ
    -0.53
     Thumb
    -0.53
    ston
    -0.53
     trans
    -0.52
    POSITIVE LOGITS
    ));
    2.71
    ]]);
    2.68
    ]);
    2.67
    ');
    2.67
    ])));
    2.67
    ");
    2.64
    ]));
    2.64
    );
    2.63
    }`);
    2.60
    ());
    2.58
    Activations Density 0.051%

    No Known Activations