© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2364
    Prev
    Next
    INDEX
    Explanations

    references to contact information and the act of reaching out or communicating

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

    instructions about how to contact someone or instructions for communication.

    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
    spender
    -0.40
     DisplayPort
    -0.36
     moyens
    -0.35
     getMin
    -0.35
     PCIe
    -0.35
     introduit
    -0.35
    isStatic
    -0.34
     pú
    -0.34
     mangá
    -0.34
     rootReducer
    -0.34
    POSITIVE LOGITS
     contacting
    0.72
    Contact
    0.70
    contact
    0.69
     contact
    0.68
     contacted
    0.68
     contacts
    0.66
     CONTACT
    0.65
     Contact
    0.64
    CONTACT
    0.63
     Infórmanos
    0.60
    Activations Density 0.111%

    No Known Activations