© 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. 443
    Prev
    Next
    INDEX
    Explanations

    instances of people departing or leaving situations

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

    leaving or departing

    np_acts-logits-general · gemini-2.0-flash

    leaving

    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
     المعيارى
    -0.48
    ModelSerializer
    -0.45
    glTexCoord
    -0.41
    IndentedString
    -0.41
     nakalista
    -0.39
    XmlAccessorType
    -0.39
    InSection
    -0.37
     تضيفلها
    -0.37
     reper
    -0.37
    ilí
    -0.36
    POSITIVE LOGITS
     exit
    0.74
     Exit
    0.68
     leave
    0.65
    exit
    0.65
    Leave
    0.63
     departure
    0.63
     Flucht
    0.62
     quitted
    0.62
     leaving
    0.62
    離開
    0.61
    Activations Density 0.303%

    No Known Activations