© 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. 3-GEMMASCOPE-RES-16K
    6. 16012
    Prev
    Next
    INDEX
    Explanations

    references to the word "cho" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.79
     Jahn
    -0.78
     États
    -0.76
    Portale
    -0.74
    fah
    -0.72
    Personensuche
    -0.71
    ContentAlignment
    -0.70
     WELLS
    -0.70
    zkopf
    -0.69
     urm
    -0.69
    POSITIVE LOGITS
     cho
    3.11
     Cho
    3.00
    Cho
    2.94
    cho
    2.39
     CHO
    1.77
     choke
    1.61
    CHO
    1.51
    chooser
    1.32
     Chop
    1.28
     Chopper
    1.27
    Activations Density 0.095%

    No Known Activations