© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 8652
    Prev
    Next
    INDEX
    Explanations

    function calls related to string manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ingredienti
    -0.56
    spira
    -0.53
    Nag
    -0.53
     vallée
    -0.50
    ----------------
    -0.49
    pl
    -0.49
     ingrédients
    -0.48
    multline
    -0.47
     ork
    -0.47
    Cod
    -0.46
    POSITIVE LOGITS
    stringify
    0.88
    ConstraintMaker
    0.87
    onedDateTime
    0.82
    NameInMap
    0.79
    ISupport
    0.78
     &___
    0.78
    IContainer
    0.76
    Itoa
    0.72
    بوابة
    0.72
    posedge
    0.72
    Activations Density 0.051%

    No Known Activations