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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10077
    Prev
    Next
    INDEX
    Explanations

    phrases related to food-related reviews and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     optical
    -0.46
    ítmény
    -0.42
     Optical
    -0.41
     opening
    -0.39
    Пар
    -0.39
    ỗ
    -0.38
    Parade
    -0.38
     Opening
    -0.38
     endorsement
    -0.38
     emp
    -0.38
    POSITIVE LOGITS
    RectangleBorder
    1.09
     متعلقه
    1.03
     שוליים
    0.92
    ंदीखरीदारी
    0.88
     '\\;'
    0.88
     TestBed
    0.84
    
    0.83
    Portale
    0.83
    DeleteBehavior
    0.82
     فريبيس
    0.80
    Activations Density 0.057%

    No Known Activations