Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10050
    Prev
    Next
    INDEX
    Explanations

    terms and properties related to programming and data structure definitions

    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
     "..\..\..\
    -0.55
    dafx
    -0.51
    JvmStatic
    -0.50
    िखित
    -0.48
     跳转至
    -0.46
     hài
    -0.46
     vegano
    -0.46
    PyExc
    -0.45
    ristol
    -0.44
    tät
    -0.44
    POSITIVE LOGITS
    ScopeManager
    0.80
    Diweddarwch
    0.76
    AddWithValue
    0.75
    GraphicsUnit
    0.72
    المكان
    0.69
    SourceChecksum
    0.68
     GetComponent
    0.65
     الرياضيه
    0.64
    mybatisplus
    0.62
    ViewChild
    0.62
    Activations Density 0.135%

    No Known Activations