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. 15-GEMMASCOPE-RES-16K
    6. 1647
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax related to data structures and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     textStatus
    -0.52
     Efq
    -0.49
     useEffect
    -0.49
     ['',
    -0.49
    ModelAttribute
    -0.49
     Ihm
    -0.48
    GraphicsUnit
    -0.48
    mappedBy
    -0.48
    parseLong
    -0.47
     Eqs
    -0.45
    POSITIVE LOGITS
    DockStyle
    0.90
    foo
    0.86
    Foo
    0.80
     Foo
    0.76
    FOO
    0.73
     foo
    0.72
     Acme
    0.64
    example
    0.64
     hello
    0.62
     test
    0.61
    Activations Density 2.145%

    No Known Activations