© 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. 18-GEMMASCOPE-RES-16K
    11. 4224
    Prev
    Next
    INDEX
    Explanations

    phrases related to face-to-face interactions

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

    "face" appearing in different contexts

    np_acts-logits-general · gemini-2.0-flash

    face to face

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getItemId
    -0.79
     ProtoMessage
    -0.78
    CloseOperation
    -0.76
    })));
    -0.73
     GenerationType
    -0.72
    chromedriver
    -0.72
    ]));
    -0.71
    }));
    -0.69
    "]));
    -0.68
     isInitialized
    -0.68
    POSITIVE LOGITS
     faces
    1.21
     Face
    1.20
     face
    1.19
    Face
    1.05
     Faces
    1.03
     FACE
    1.03
    face
    1.02
    faces
    0.96
    FACE
    0.92
    Faces
    0.86
    Activations Density 0.174%

    No Known Activations