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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1526
    Prev
    Next
    INDEX
    Explanations

    references to personal opinions and experiences

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

    Personal pronouns followed by a contraction or verb

    np_acts-logits-general · gemini-2.0-flash

    personal pronouns

    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
    DockStyle
    -0.69
     intptr
    -0.67
     >=",
    -0.65
    Chham
    -0.65
     للاسماء
    -0.63
    complexContent
    -0.63
    zeum
    -0.63
    complexType
    -0.63
    دانشنامهٔ
    -0.61
    iedenen
    -0.61
    POSITIVE LOGITS
     infatti
    1.04
     totiž
    0.96
     bowiem
    0.95
     ведь
    0.87
    だって
    0.85
     namelijk
    0.82
    Ведь
    0.82
     certainly
    0.81
     ugy
    0.71
    certainly
    0.71
    Activations Density 0.352%

    No Known Activations