© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1190
    Prev
    Next
    INDEX
    Explanations

    expressions of strong profanity and dismissive attitudes

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

    Profanity and vulgarity

    np_acts-logits-general · gemini-2.0-flash

    profanity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PyTuple
    -0.58
    ihr
    -0.52
    newBuilder
    -0.49
     '"'
    -0.48
    AxisAlignment
    -0.48
    Leap
    -0.48
     Seh
    -0.47
      
    -0.46
    oa̍t
    -0.46
    Shear
    -0.46
    POSITIVE LOGITS
    OGND
    0.94
     shit
    0.83
    fucker
    0.82
    FUCK
    0.79
     fucking
    0.78
    shit
    0.77
    fuck
    0.77
     SHIT
    0.77
    Shit
    0.76
     Shit
    0.76
    Activations Density 0.165%

    No Known Activations