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. 2018
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing quality and value in dining experiences

    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
     hombro
    -0.59
     continúas
    -0.58
     resourceCulture
    -0.57
     vitales
    -0.52
    WithIOException
    -0.52
    ագրություններ
    -0.50
    toHaveBeenCalled
    -0.50
     kasarigan
    -0.49
    UserScript
    -0.48
    }^{+\
    -0.48
    POSITIVE LOGITS
     location
    1.21
     atmosphere
    1.12
     surroundings
    1.06
     environment
    1.00
     ambiance
    0.99
     scenery
    0.98
     ambience
    0.97
     place
    0.95
     decor
    0.93
     interior
    0.88
    Activations Density 0.068%

    No Known Activations