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. 3142
    Prev
    Next
    INDEX
    Explanations

    affirmative responses and expressions of agreement

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

    "Yeah" followed by a comma

    np_acts-logits-general · gemini-2.0-flash

    yeah,

    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
    ſelves
    -0.84
    )";
    
    -0.82
     myſelf
    -0.79
     Majefty
    -0.76
    MLLoader
    -0.75
     〈
    -0.74
    ')")
    -0.74
    」,
    -0.71
    InputTagHelper
    -0.70
    )");
    
    -0.70
    POSITIVE LOGITS
    ,
    1.10
     yeah
    0.97
     yes
    0.86
     Yeah
    0.83
    Yeah
    0.78
    yeah
    0.74
     I
    0.73
     Yes
    0.72
    ...
    0.68
    Yes
    0.66
    Activations Density 0.117%

    No Known Activations