© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 2866
    Prev
    Next
    INDEX
    Explanations

    references to children and family relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })));
    -0.39
     Réponses
    -0.37
    RequestMapping
    -0.35
    DataAnnotations
    -0.35
    )_/¯
    -0.35
     consultato
    -0.35
    axel
    -0.35
    GMENT
    -0.34
     {}));
    -0.33
    }));
    -0.33
    POSITIVE LOGITS
     child
    2.58
     kids
    2.58
     children
    2.56
     kid
    2.33
    kids
    2.30
     toddler
    2.27
    Kids
    2.25
     CHILD
    2.23
     enfants
    2.22
     çocuk
    2.22
    Activations Density 1.239%

    No Known Activations