Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 3536
    Prev
    Next
    INDEX
    Explanations

    instances of the word "send" and related variations indicating transmission or communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ghton
    -0.83
    ']))
    
    -0.80
    AndEndTag
    -0.80
    Toole
    -0.77
     McIntyre
    -0.76
    mær
    -0.74
    NOPQRST
    -0.74
    RetentionPolicy
    -0.74
    ___]
    -0.74
    glä
    -0.73
    POSITIVE LOGITS
    send
    1.65
    Send
    1.46
     SEND
    1.44
    SEND
    1.43
     Send
    1.41
     send
    1.33
     Sends
    1.12
     sends
    1.02
     发送
    1.00
    recv
    1.00
    Activations Density 0.041%

    No Known Activations