© 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. 3-GEMMASCOPE-RES-16K
    6. 13267
    Prev
    Next
    INDEX
    Explanations

    the term "sister" referenced in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })));
    -0.80
    Показать
    -0.71
    ')")
    -0.71
    })*/
    -0.69
    apunov
    -0.69
    }}/>
    -0.68
    ')):
    -0.65
    //
    -0.64
    ])):
    -0.64
    umel
    -0.63
    POSITIVE LOGITS
     sister
    3.08
     sisters
    2.85
     Sister
    2.78
    Sister
    2.67
    sister
    2.66
     Sisters
    2.43
    Sisters
    2.29
     brother
    2.28
    sisters
    2.25
    brother
    2.13
    Activations Density 0.050%

    No Known Activations