© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2648
    Prev
    Next
    INDEX
    Explanations

    quantities related to energy and pressure in scientific contexts

    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
    GHIJKLM
    -0.51
     super
    -0.47
     part
    -0.46
     multi
    -0.45
    étrie
    -0.44
     motion
    -0.44
     invokingState
    -0.43
    thiet
    -0.42
     pick
    -0.41
    Externí
    -0.41
    POSITIVE LOGITS
     متعلقه
    0.77
     Roskov
    0.73
    thâu
    0.73
    msub
    0.72
    TagMode
    0.67
    ṁ
    0.67
    IsContent
    0.65
     virgins
    0.65
    ceq
    0.64
    clusal
    0.64
    Activations Density 1.141%

    No Known Activations