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. 3580
    Prev
    Next
    INDEX
    Explanations

    references to estimation techniques in statistical or mathematical contexts

    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
     doInBackground
    -0.81
     harvests
    -0.79
    IntoConstraints
    -0.68
    GEBURTSDATUM
    -0.68
    BeginContext
    -0.67
     adjourn
    -0.66
    ValueStyle
    -0.66
     Shakspeare
    -0.66
     Patrice
    -0.66
     acceptez
    -0.65
    POSITIVE LOGITS
    tilde
    0.79
     Portal
    0.78
     portal
    0.76
    Portal
    0.73
     carrier
    0.68
    types
    0.64
    portal
    0.61
     Shi
    0.59
    carrier
    0.57
    ampton
    0.56
    Activations Density 0.131%

    No Known Activations