Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14176
    Prev
    Next
    INDEX
    Explanations

    specific verbs related to professional transitions and changes in employment status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISupport
    -0.63
    ModelAdmin
    -0.60
    IANGLES
    -0.60
     fortsatt
    -0.58
    AddHtmlAttribute
    -0.56
     تضيفلها
    -0.55
    saraba
    -0.54
     morrow
    -0.54
    وفاته
    -0.53
     perpetuity
    -0.52
    POSITIVE LOGITS
     last
    2.83
     recently
    2.71
    recently
    2.40
    Recently
    2.27
     Recently
    2.26
     recent
    2.25
    last
    2.25
    Last
    2.14
     recentemente
    2.08
     récemment
    2.07
    Activations Density 0.702%

    No Known Activations