© 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. 5-GEMMASCOPE-RES-16K
    6. 9770
    Prev
    Next
    INDEX
    Explanations

    code components related to extra data handling in programming contexts, particularly in Android development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amin
    -0.53
    RSpec
    -0.50
     Mem
    -0.49
     a
    -0.49
    Mem
    -0.49
    addGroup
    -0.49
    di
    -0.48
    testng
    -0.48
    ns
    -0.47
    subsection
    -0.47
    POSITIVE LOGITS
    putExtra
    2.62
    Personendaten
    1.15
     @"/
    1.13
    BufferException
    1.09
     kasarigan
    1.06
    principalColumn
    1.03
    FontOfSize
    1.03
     TextAppearance
    1.01
    EndGlobalSection
    1.01
    IsMutable
    0.98
    Activations Density 0.013%

    No Known Activations