Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 5597
    Prev
    Next
    INDEX
    Explanations

    phrases related to making choices or selections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.84
    yethylene
    -0.65
    ecake
    -0.64
     Pedersen
    -0.64
    lossenen
    -0.63
     I
    -0.63
    แดง
    -0.62
     Barclay
    -0.62
    indrome
    -0.61
    simd
    -0.60
    POSITIVE LOGITS
    choose
    2.07
     choose
    2.05
     Choose
    2.04
    Choose
    2.01
     chooses
    1.99
     choosing
    1.95
    choosing
    1.92
     CHOOSE
    1.90
     Choosing
    1.87
     choices
    1.86
    Activations Density 0.081%

    No Known Activations