© 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. 23-GEMMASCOPE-RES-16K
    6. 10735
    Prev
    Next
    INDEX
    Explanations

    instances of the string "Str" in various contexts, likely related to string manipulation functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TextInputType
    -0.59
     rendu
    -0.58
    ")"
    -0.58
    awake
    -0.58
    webElementXpaths
    -0.57
    ModelAdmin
    -0.57
     AssemblyTitle
    -0.56
    nocache
    -0.56
    astron
    -0.56
    Obrázky
    -0.54
    POSITIVE LOGITS
    ftime
    0.65
     linkovi
    0.59
     Kens
    0.56
     sams
    0.55
    ptime
    0.53
    Freezing
    0.52
     asos
    0.51
    ButtonModule
    0.51
     Архів
    0.51
     Yah
    0.51
    Activations Density 0.038%

    No Known Activations