© 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. 11078
    Prev
    Next
    INDEX
    Explanations

    the word "only" in various contexts

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

    "only"

    np_acts-logits-general · gemini-2.0-flash

    exclusivity or limitation

    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
     accél
    -0.46
    HCl
    -0.42
     äta
    -0.42
     hashCode
    -0.42
    ᵤ
    -0.41
    }])
    -0.41
    "}")
    -0.40
     arbet
    -0.40
     isChecked
    -0.40
     בח
    -0.40
    POSITIVE LOGITS
     only
    0.95
    Only
    0.93
    only
    0.91
     Only
    0.88
    ONLY
    0.84
     onlyOwner
    0.82
     ONLY
    0.82
     רק
    0.79
    etlen
    0.78
    Hanya
    0.76
    Activations Density 0.107%

    No Known Activations