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. 16-GEMMASCOPE-RES-16K
    6. 1777
    Prev
    Next
    INDEX
    Explanations

    mathematical or statistical comparisons between different groups or conditions

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

    Mathematical/scientific expressions using $

    np_acts-logits-general · gemini-2.0-flash

    between $x$ and $y$

    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
    <bos>
    -0.47
     iload
    -0.45
     network
    -0.44
     BorderSide
    -0.44
     Network
    -0.42
     Fairchild
    -0.42
    Placa
    -0.42
    ÔNG
    -0.42
    icrous
    -0.41
    asticity
    -0.41
    POSITIVE LOGITS
    bootstrapcdn
    0.76
     sebaliknya
    0.66
     Référence
    0.66
     propOrder
    0.61
    UVWXYZ
    0.61
    yntaxException
    0.60
    LookAnd
    0.59
    IVEREF
    0.58
    respectively
    0.57
    vician
    0.57
    Activations Density 0.715%

    No Known Activations