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. 6-GEMMASCOPE-RES-16K
    6. 13335
    Prev
    Next
    INDEX
    Explanations

    file paths and file extensions commonly associated with programming or software projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.63
    vatar
    -0.55
     Carton
    -0.54
    TabIndex
    -0.53
    ={`/
    -0.51
     onCancelled
    -0.51
    めんなさい
    -0.50
     Fragment
    -0.49
    memberof
    -0.48
     scattata
    -0.48
    POSITIVE LOGITS
    ValueStyle
    1.71
    AddTagHelper
    1.62
    assertThat
    0.96
    pyplot
    0.94
    WireFormatLite
    0.81
    EndInit
    0.78
    Assertions
    0.78
     GenerationType
    0.75
    SEVERE
    0.74
    RefNanny
    0.72
    Activations Density 0.026%

    No Known Activations