© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 15699
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or accommodation

    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
     houſe
    -0.74
     iſt
    -0.73
     myſelf
    -0.70
     purpoſe
    -0.70
     ſche
    -0.70
     cauſe
    -0.69
     Monfieur
    -0.68
     faptul
    -0.67
     ſtate
    -0.66
     čierna
    -0.65
    POSITIVE LOGITS
    ที่มี
    0.75
     Has
    0.69
     có
    0.68
    __((
    0.66
     with
    0.65
    with
    0.64
    createCanvas
    0.64
     has
    0.62
     inclusive
    0.60
    با
    0.59
    Activations Density 0.370%

    No Known Activations