© 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. 16-GEMMASCOPE-RES-16K
    11. 14738
    Prev
    Next
    INDEX
    Explanations

    mentions of applications and services related to web hosting and file management

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

    Following certain words (comma, as, and)

    np_acts-logits-general · gemini-2.0-flash

    sound recognition services and brands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RouterModule
    -0.50
    HomeAsUpEnabled
    -0.44
     ujednoznacz
    -0.42
     ô
    -0.42
    ötz
    -0.42
     judicial
    -0.42
     ins
    -0.42
    DataPropertyName
    -0.41
     AppComponent
    -0.41
     pres
    -0.41
    POSITIVE LOGITS
     himſelf
    0.80
     protoimpl
    0.76
     themſelves
    0.76
    دانشنامهٔ
    0.74
     handen
    0.73
     Efq
    0.72
    :✨
    0.72
    localctx
    0.71
     passés
    0.71
     itſelf
    0.71
    Activations Density 0.949%

    No Known Activations