© 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. 18-GEMMASCOPE-RES-16K
    11. 10780
    Prev
    Next
    INDEX
    Explanations

    structured code segments or expressions

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

    "return" in code

    np_acts-logits-general · gemini-2.0-flash

    return this; method chaining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleable
    -0.59
    cillas
    -0.57
    zysta
    -0.54
    ENES
    -0.53
    wixt
    -0.50
    новништво
    -0.49
    ATORY
    -0.49
     insuffisamment
    -0.49
    angas
    -0.48
    IPMENT
    -0.47
    POSITIVE LOGITS
    return
    0.95
    tagHelperRunner
    0.78
     defaultstate
    0.75
     return
    0.69
     =
    0.69
     CreateTagHelper
    0.68
    fromnode
    0.68
    MessageTagHelper
    0.67
    IVEREF
    0.63
     is
    0.63
    Activations Density 0.020%

    No Known Activations