© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 13748
    Prev
    Next
    INDEX
    Explanations

    elements related to social media and online interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    noinspection
    -0.70
    aarrggbb
    -0.69
    Spoljašnje
    -0.65
    XmlRootElement
    -0.62
     propOrder
    -0.60
     Numerade
    -0.59
    "]();
    -0.59
     "}";
    -0.57
    ]")]
    -0.56
    mannian
    -0.56
    POSITIVE LOGITS
     resourceCulture
    0.56
     SqlCommand
    0.50
    WriteAttribute
    0.50
    ThroughAttribute
    0.48
     newOwner
    0.46
    drawString
    0.45
    likasi
    0.45
    
    0.44
     Walther
    0.42
    thums
    0.42
    Activations Density 0.195%

    No Known Activations