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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8597
    Prev
    Next
    INDEX
    Explanations

    the word "around" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     незавершена
    -0.47
    enskap
    -0.37
     tjen
    -0.36
    Cert
    -0.32
    ciaio
    -0.32
     fatis
    -0.32
    simmon
    -0.31
    这不
    -0.31
     fédé
    -0.31
     ſal
    -0.31
    POSITIVE LOGITS
     around
    3.92
    Around
    3.61
    around
    3.56
     Around
    3.53
     AROUND
    3.42
    AROUND
    2.98
     alrededor
    2.88
     autour
    2.80
     вокруг
    2.66
     intorno
    2.59
    Activations Density 0.067%

    No Known Activations