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. 21-GEMMASCOPE-RES-16K
    6. 14214
    Prev
    Next
    INDEX
    Explanations

    specific sounds or phonetic patterns in the text

    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
     Lawson
    -0.46
     bande
    -0.40
     ли
    -0.38
     min
    -0.38
    百合
    -0.36
     Landes
    -0.36
    garten
    -0.36
     imp
    -0.36
    tover
    -0.35
    uni
    -0.34
    POSITIVE LOGITS
    led
    1.22
    les
    1.05
    LES
    0.94
    ling
    0.93
    leness
    0.91
    Personensuche
    0.91
    leb
    0.90
    LED
    0.89
    تقاوى
    0.88
    lers
    0.88
    Activations Density 0.323%

    No Known Activations