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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 556
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and quotation marks in the text

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

    Apostrophes and single quotes

    np_acts-logits-general · gemini-2.0-flash

    single quotes

    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
    {}".
    -0.86
    }}"
    -0.85
    \""
    -0.81
    UpInside
    -0.78
      “
    -0.75
    ==",
    -0.74
     "}
    -0.73
    BeginInit
    -0.72
    “
    -0.72
    ]["
    -0.69
    POSITIVE LOGITS
     '
    1.19
    =’
    1.14
    ==='
    1.13
    ...'
    1.12
     '.
    1.11
     '
    
    1.08
     ‘
    1.07
     ';
    1.05
    |'
    1.05
     ',
    1.03
    Activations Density 0.392%

    No Known Activations