© 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. 25-GEMMASCOPE-RES-16K
    11. 4748
    Prev
    Next
    INDEX
    Explanations

    phrases related to success and failure messages in email or account management contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .”)
    -2.04
    </h2>
    -1.98
    "));
    -1.95
    ')
    -1.84
    "),
    -1.84
    '),
    -1.82
    ")
    -1.81
    "):
    -1.76
    ”),
    -1.76
    ."),
    -1.74
    POSITIVE LOGITS
    ";
    1.95
    ';
    1.68
     ";
    1.53
    .";
    1.52
    `;
    1.42
    </blockquote>
    1.41
    ?";
    1.40
    !";
    1.40
    /";
    1.37
    :";
    1.37
    Activations Density 0.183%

    No Known Activations