© 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. 24-GEMMASCOPE-RES-16K
    6. 16245
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and statistical notations related to expected values and probability distributions

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

    "E" after various symbols or notations

    np_acts-logits-general · gemini-2.0-flash

    E and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     makeStyles
    -0.53
    AnimationsModule
    -0.51
    eg
    -0.49
    fromnode
    -0.47
    enumii
    -0.46
    eq
    -0.46
    eled
    -0.46
    ölker
    -0.45
    astify
    -0.44
     ویکی‌پدیای
    -0.44
    POSITIVE LOGITS
     E
    2.75
    E
    2.43
    E
    1.64
     Е
    1.60
     Э
    1.39
    getE
    1.39
    𝐸
    1.26
     É
    1.24
     Ε
    1.22
    Е
    1.19
    Activations Density 0.578%

    No Known Activations