© 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. 21-GEMMASCOPE-RES-16K
    6. 6282
    Prev
    Next
    INDEX
    Explanations

    elements related to complex systems or structures, particularly 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
    ########.
    -0.49
     Efq
    -0.47
     itſelf
    -0.44
    urlencoded
    -0.40
    ClientRect
    -0.40
    pyplot
    -0.40
     onlyOwner
    -0.40
    yarnpkg
    -0.38
    idopsis
    -0.38
    cloudfront
    -0.37
    POSITIVE LOGITS
     M
    1.01
    M
    0.99
     m
    0.89
     mM
    0.84
     MM
    0.81
     म
    0.80
    ม
    0.77
     MR
    0.76
     MO
    0.76
     MD
    0.74
    Activations Density 2.381%

    No Known Activations