© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7024
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to reaching out and maintaining contact

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

    "Get in touch" or means of contact

    np_acts-logits-general · gemini-2.0-flash

    contacting or communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Искәрмәләр
    -0.40
    DockStyle
    -0.38
     Cassette
    -0.33
    Смотрите
    -0.33
     dumping
    -0.33
     Einwilligung
    -0.33
     setting
    -0.32
     버
    -0.32
    Preco
    -0.32
     perfectly
    -0.32
    POSITIVE LOGITS
     contacted
    1.03
     contacting
    0.92
     contact
    0.91
     Contact
    0.85
    Contact
    0.85
    contact
    0.84
     CONTACT
    0.83
     contacts
    0.78
     menghubungi
    0.76
     contactar
    0.75
    Activations Density 0.227%

    No Known Activations