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. 4-GEMMASCOPE-RES-16K
    6. 11907
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the present state or ongoing actions of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kear
    -0.65
     Sarg
    -0.64
    Exc
    -0.61
    ب
    -0.60
    Kast
    -0.59
    TEX
    -0.58
     Bris
    -0.58
     Ress
    -0.58
     Vib
    -0.58
    QX
    -0.56
    POSITIVE LOGITS
     currently
    1.97
    currently
    1.81
     presently
    1.75
     Currently
    1.69
    Currently
    1.61
     Presently
    1.38
     attualmente
    1.37
     actualmente
    1.35
     atualmente
    1.29
     actuellement
    1.29
    Activations Density 0.089%

    No Known Activations