© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9537
    Prev
    Next
    INDEX
    Explanations

    second person address and expressions of possibility or capability

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

    "You" followed by modal verbs

    np_acts-logits-general · gemini-2.0-flash

    you {modal verb}

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.55
    новниш
    -0.54
    getSystemService
    -0.51
    الحياه
    -0.50
    guisement
    -0.48
     defaultstate
    -0.48
     IBOutlet
    -0.47
    principalColumn
    -0.45
     MessageBoxIcon
    -0.44
    ędzie
    -0.43
    POSITIVE LOGITS
     חיצוניים
    0.67
     Wiktionnaire
    0.61
     cannot
    0.60
    ftagPool
    0.60
    oples
    0.59
    }\]
    0.57
     apostar
    0.57
    ibrill
    0.56
    rungsseite
    0.56
     mustn
    0.55
    Activations Density 0.146%

    No Known Activations