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. 22-GEMMASCOPE-RES-16K
    6. 3311
    Prev
    Next
    INDEX
    Explanations

    references to food and culinary experiences

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

    First-person singular pronoun "I" or "'m" or "is"

    np_acts-logits-general · gemini-2.0-flash

    expressing thoughts and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.91
    TacToe
    -0.89
    />";
    -0.85
    ]-->
    -0.84
     />";
    -0.80
     '\\;'
    -0.78
    OGND
    -0.75
    ]<<"
    -0.72
     Ведь
    -0.72
    []):
    -0.70
    POSITIVE LOGITS
     fucking
    0.81
     weirdly
    0.78
     goddamn
    0.74
     apparently
    0.73
    fucking
    0.71
     FUCKING
    0.68
     vaguely
    0.67
     ostensibly
    0.66
     legitimately
    0.65
     variously
    0.64
    Activations Density 0.245%

    No Known Activations