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. 2-GEMMASCOPE-RES-16K
    6. 3666
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'g.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QMetaType
    -0.68
     nahilalakip
    -0.61
     IndexPath
    -0.61
     يتيمه
    -0.59
    DeleteBehavior
    -0.58
     “¿
    -0.53
     scania
    -0.52
     pij
    -0.52
     betre
    -0.52
     Chriftian
    -0.51
    POSITIVE LOGITS
     g
    2.31
    #
    0.95
     г
    0.88
     gli
    0.82
     nakalista
    0.74
     gâ
    0.72
     Ghat
    0.71
     Gha
    0.69
     gated
    0.66
    قبال
    0.66
    Activations Density 0.216%

    No Known Activations