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. 21-GEMMASCOPE-RES-16K
    6. 7520
    Prev
    Next
    INDEX
    Explanations

    specific elements related to mathematical operations or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ISLAND
    -0.82
     ISNI
    -0.82
     iodine
    -0.82
     Islands
    -0.81
     islands
    -0.78
     INSTITUTE
    -0.78
     Industries
    -0.78
    IDENTITY
    -0.77
     iodide
    -0.77
     Industrie
    -0.77
    POSITIVE LOGITS
    basicConfig
    0.57
    Amérique
    0.53
     Touchable
    0.51
    Portale
    0.50
    esterno
    0.49
    ableness
    0.44
     đào
    0.44
    artney
    0.43
    xas
    0.42
    ares
    0.41
    Activations Density 0.384%

    No Known Activations