© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5240
    Prev
    Next
    INDEX
    Explanations

    references to characters labeled as girls or females, often in the context of stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "girl" and its variations, consistently activating strongly across different contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.56
    });
    -0.52
     Stonehenge
    -0.50
    anyahu
    -0.49
    日閲覧
    -0.48
     CNA
    -0.48
     Petra
    -0.47
    ()));
    -0.47
     Thrones
    -0.47
     condolences
    -0.47
    POSITIVE LOGITS
     girl
    1.07
    Girl
    1.03
     Girl
    1.01
    Girls
    1.01
     girls
    1.01
    Boy
    1.01
     boy
    0.99
     Girls
    0.98
    girl
    0.95
     Boy
    0.91
    Activations Density 0.032%

    No Known Activations