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. 22-GEMMASCOPE-RES-16K
    6. 3738
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions, particularly in a statistical or scientific context

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

    Mathematical or statistical notation

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation `a` followed by `_{`

    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
    ::<
    -0.51
    glGen
    -0.49
    <?
    -0.48
    \|^{
    -0.47
    Hochspringen
    -0.46
    ngdoc
    -0.43
     oignons
    -0.41
    FunctionFlags
    -0.41
    IntoConstraints
    -0.40
    sizeCache
    -0.40
    POSITIVE LOGITS
    TargetException
    0.89
    Autoritní
    0.80
     Reverso
    0.80
    NUMX
    0.65
    قایناق‌لار
    0.65
     ,
    0.64
    cerely
    0.64
    theless
    0.61
    awtextra
    0.61
     ^
    0.60
    Activations Density 0.079%

    No Known Activations