© 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. 4101
    Prev
    Next
    INDEX
    Explanations

    instances of the word "leave" and its variations in various contexts

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

    "leave"

    np_acts-logits-general · gemini-2.0-flash

    leaving or moving away

    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
    tagext
    -0.84
    Personensuche
    -0.79
    Datuak
    -0.77
    ftagPool
    -0.74
    MemoryWarning
    -0.71
    setVerticalGroup
    -0.67
    Życiorys
    -0.65
    érard
    -0.64
    ThroughAttribute
    -0.64
     mira
    -0.63
    POSITIVE LOGITS
     leaves
    1.16
     leave
    1.09
    Leaves
    1.05
    leave
    1.04
     LEAVE
    1.03
    leaves
    1.02
     Leaves
    1.00
    Leave
    0.99
     Leave
    0.97
     leaving
    0.95
    Activations Density 0.104%

    No Known Activations