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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1395
    Prev
    Next
    INDEX
    Explanations

    coding structures and components, particularly those related to functions and data types

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

    elle::das::make_tuple

    np_acts-logits-general · gemini-2.0-flash

    code identifiers and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDEFAULT
    -0.50
     externi
    -0.43
     ivelany
    -0.41
     Quan
    -0.38
    BASEPATH
    -0.37
    Quack
    -0.35
     Mau
    -0.35
     proc
    -0.35
    ConstraintMaker
    -0.35
     Qui
    -0.35
    POSITIVE LOGITS
    featureID
    0.64
     mitochond
    0.61
     Output
    0.59
     "*"
    0.58
     تضيفلها
    0.57
    +:+
    0.57
     McF
    0.56
    : 
    0.56
     $\{\
    0.55
    /.../
    0.55
    Activations Density 0.441%

    No Known Activations