© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9239
    Prev
    Next
    INDEX
    Explanations

    relationships and communication in collaborative settings

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

    Tokens indicating the number three

    np_acts-logits-general · gemini-2.0-flash

    three, trio, tri

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ambos
    -0.84
     Both
    -0.82
    Both
    -0.79
    Ambos
    -0.78
     both
    -0.74
     MainAxisSize
    -0.72
     entrambi
    -0.71
    both
    -0.71
     Beide
    -0.69
     entram
    -0.67
    POSITIVE LOGITS
     three
    1.67
    three
    1.58
     trio
    1.52
    Three
    1.40
     trois
    1.38
     THREE
    1.37
     Three
    1.37
    三
    1.29
    THREE
    1.28
     três
    1.27
    Activations Density 1.519%

    No Known Activations