Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3184
    Prev
    Next
    INDEX
    Explanations

    phrases that convey analysis or interpretation of social contexts and laws, particularly in the realm of literature and historical narratives

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

    Text after periods, brackets, or quotation marks

    np_acts-logits-general · gemini-2.0-flash

    legal citation or disclaimer

    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
    -0.94
     iſt
    -0.88
     themſelves
    -0.87
     Houſe
    -0.87
     houſe
    -0.84
     Efq
    -0.81
     itſelf
    -0.81
     poffe
    -0.80
     ſhe
    -0.80
     ſta
    -0.79
    POSITIVE LOGITS
     "[
    0.57
     “[
    0.55
    正如
    0.54
    だからこそ
    0.53
     Thus
    0.53
    “[
    0.52
     “
    0.51
     "
    0.51
    Similarly
    0.51
     Similarly
    0.50
    Activations Density 0.294%

    No Known Activations