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. 25-GEMMASCOPE-RES-16K
    6. 3665
    Prev
    Next
    INDEX
    Explanations

    patterns in numerical data and formal structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Forth
    -0.96
    Forth
    -0.90
     Five
    -0.75
    ########.
    -0.75
    Five
    -0.74
     forth
    -0.73
    FOUR
    -0.73
    Fourth
    -0.72
     Six
    -0.70
    forth
    -0.68
    POSITIVE LOGITS
    tribune
    0.56
    WireFormat
    0.49
     lateinit
    0.48
    ầng
    0.47
    кипе
    0.47
    جمعیت
    0.46
    ecé
    0.46
     getColumn
    0.46
     intérêts
    0.45
     vzd
    0.44
    Activations Density 0.429%

    No Known Activations