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. 3-GEMMASCOPE-RES-16K
    6. 8206
    Prev
    Next
    INDEX
    Explanations

    phrases expressing feelings and experiences, particularly in relation to understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defStyle
    -0.69
     defStyleAttr
    -0.58
    ьаж
    -0.54
    肘
    -0.54
     científica
    -0.53
     portátiles
    -0.52
     dzi
    -0.51
    Hochspringen
    -0.51
     آبی
    -0.50
     elbows
    -0.49
    POSITIVE LOGITS
    uxxxx
    0.73
    клопе
    0.73
    TagMode
    0.72
     invokingState
    0.68
    RenderAtEndOf
    0.67
     forKey
    0.67
    addPreferredGap
    0.65
    GraphicsUnit
    0.63
     kaarangay
    0.62
    ритори
    0.61
    Activations Density 0.348%

    No Known Activations