© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13160
    Prev
    Next
    INDEX
    Explanations

    difficult situations or challenges

    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
     дописавши
    -0.48
    verage
    -0.48
     مشين
    -0.47
     Infórmanos
    -0.46
    Sabes
    -0.46
     Vorgang
    -0.45
    sidemargin
    -0.44
     שוליים
    -0.44
    tesy
    -0.44
     pater
    -0.44
    POSITIVE LOGITS
     difficult
    2.75
    difficult
    2.46
     Difficult
    2.41
    Difficult
    2.31
     difficulty
    2.29
     difícil
    2.02
     difficile
    2.00
     diffic
    1.93
     difficiles
    1.92
     Difficulty
    1.92
    Activations Density 0.395%

    No Known Activations