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. 16-GEMMASCOPE-RES-16K
    6. 6535
    Prev
    Next
    INDEX
    Explanations

    references to character development and emotional interactions

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

    Text following periods, commas, or brackets

    np_acts-logits-general · gemini-2.0-flash

    read of, with

    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
    NUMX
    -0.58
    iStock
    -0.57
     Rout
    -0.57
     snippetHide
    -0.57
    Actualmente
    -0.57
    Читати
    -0.56
     فريبيس
    -0.55
    haustible
    -0.53
    unz
    -0.52
    astru
    -0.52
    POSITIVE LOGITS
    InjectAttribute
    0.63
     Overall
    0.60
     propOrder
    0.59
    Overall
    0.59
     LOVED
    0.58
     adoro
    0.57
    blico
    0.57
    cdnjs
    0.56
     <<<<<<<<<<<<<<
    0.55
    Kudos
    0.55
    Activations Density 0.212%

    No Known Activations