© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1485
    Prev
    Next
    INDEX
    Explanations

    symbolic representation of programming constructs and structures

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

    Tokens after commas, parenthesis, or dollar signs

    np_acts-logits-general · gemini-2.0-flash

    parentheticals and code blocks

    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
    __':
    -0.48
    Portály
    -0.43
    ėk
    -0.42
    hyrchwyd
    -0.42
    __':
    -0.41
    ChildScrollView
    -0.41
     gynhyrchwyd
    -0.41
    ':
    -0.40
    rzez
    -0.40
    </em>
    -0.40
    POSITIVE LOGITS
    false
    1.67
    true
    1.65
     true
    1.56
     false
    1.55
    True
    1.44
    False
    1.43
     True
    1.37
     TRUE
    1.33
     False
    1.31
    TRUE
    1.28
    Activations Density 0.338%

    No Known Activations