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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 15994
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation used in coding or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setResizable
    -0.55
    IsMutable
    -0.53
     apparent
    -0.51
    BeginInit
    -0.49
    snackbar
    -0.48
     liberi
    -0.48
     BorderRadius
    -0.47
    HasOne
    -0.47
    CORBA
    -0.47
    ⎦
    -0.46
    POSITIVE LOGITS
    mybatisplus
    0.93
     Picchu
    0.79
     Vind
    0.69
    aimerais
    0.67
    PickerController
    0.66
    cipar
    0.66
    Smarty
    0.65
    romyalgia
    0.64
     Sorgen
    0.61
     Audiodateien
    0.61
    Activations Density 0.098%

    No Known Activations