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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 15827
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with emphasis on indices and subscript variables

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

    Text within mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical formulas

    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
     Carr
    -0.82
     calendriers
    -0.74
    +}\
    -0.72
    )”
    -0.70
    ChildScrollView
    -0.70
    {}".
    -0.69
    ).”
    -0.69
    )”.
    -0.68
    ].)
    -0.66
    "):
    
    -0.66
    POSITIVE LOGITS
    _{
    1.56
     _{
    1.21
    }_{
    1.02
     numberWith
    0.90
    <sub>
    0.86
    _{\
    0.83
    )_{
    0.82
     }_{
    0.80
    ^{
    0.80
    ۜ
    0.76
    Activations Density 0.714%

    No Known Activations