© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9297
    Prev
    Next
    INDEX
    Explanations

    quotation marks or similar punctuation indicating dialogue and cited speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    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
    -0.96
     pleaſure
    -0.87
     purpoſe
    -0.81
     ſche
    -0.80
     ſmall
    -0.79
     ſtate
    -0.78
     becauſe
    -0.77
     Theſe
    -0.76
     cauſe
    -0.75
     myſelf
    -0.75
    POSITIVE LOGITS
    mybatisplus
    0.76
     <<<<<<<<<<<<<<
    0.57
    testify
    0.52
    consider
    0.50
     setuptools
    0.49
    definitely
    0.48
     préférence
    0.47
    still
    0.47
    hes
    0.47
     TextView
    0.47
    Activations Density 0.330%

    No Known Activations