© 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. 20-GEMMASCOPE-RES-16K
    11. 13885
    Prev
    Next
    INDEX
    Explanations

    phrases related to offers of assistance and communication

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

    "Free" followed by "to" or start of turn followed by "user"

    np_acts-logits-general · gemini-2.0-flash

    feel free to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    pantalones
    -0.54
     يتيمه
    -0.52
     Picchu
    -0.51
    Espèce
    -0.50
    astify
    -0.49
    Evid
    -0.48
     stockholm
    -0.47
    mante
    -0.46
    mobileqq
    -0.45
     SqlParameter
    -0.45
    POSITIVE LOGITS
    ScopeManager
    0.42
     any
    0.40
     jederzeit
    0.37
     elástica
    0.37
     anytime
    0.37
     pensée
    0.37
     bienven
    0.37
     Anytime
    0.36
    Feel
    0.35
    RTEE
    0.33
    Activations Density 0.154%

    No Known Activations