© 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. 18-GEMMASCOPE-RES-16K
    11. 8933
    Prev
    Next
    INDEX
    Explanations

    phrases indicating clarification or elaboration on previous statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "In other words" or similar rephrasing

    np_acts-logits-general · gemini-2.0-flash

    in other words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.96
     houſe
    -0.95
     Houſe
    -0.95
     itſelf
    -0.95
     Efq
    -0.93
     pleaſure
    -0.91
     ―――――
    -0.90
     Majefty
    -0.89
     ་་
    -0.87
    ſelves
    -0.86
    POSITIVE LOGITS
     they
    1.03
     it
    0.95
     the
    0.94
    :
    0.91
     we
    0.86
    ,
    0.86
     a
    0.85
     “
    0.78
     "
    0.77
     how
    0.75
    Activations Density 0.228%

    No Known Activations