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. 14766
    Prev
    Next
    INDEX
    Explanations

    expressions related to falling, whether in love or metaphorically in challenging situations

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

    "fall" and its forms

    np_acts-logits-general · gemini-2.0-flash

    fall for

    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
     دیکھیے
    -0.74
    ushima
    -0.56
    Luong
    -0.51
    chließend
    -0.50
    maxSize
    -0.49
    CLE
    -0.49
    Thee
    -0.48
     supre
    -0.48
     Prit
    -0.48
    keteers
    -0.48
    POSITIVE LOGITS
    FALL
    1.41
     FALL
    1.38
    falls
    1.31
     falls
    1.29
    fall
    1.29
     fall
    1.29
    falling
    1.28
    Falling
    1.26
    Falls
    1.25
     falling
    1.24
    Activations Density 0.064%

    No Known Activations