© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 12489
    Prev
    Next
    INDEX
    Explanations

    asserts related to table entries and validation checks for null values

    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
    chond
    -0.39
    mbg
    -0.38
     Tax
    -0.37
    phorus
    -0.37
     tax
    -0.37
    └──
    -0.37
    перь
    -0.36
    pNext
    -0.35
     getLayout
    -0.35
    ogia
    -0.35
    POSITIVE LOGITS
    saraba
    0.97
    Rhestr
    0.96
    MessageOf
    0.95
    IntoConstraints
    0.93
    PerformLayout
    0.91
     تضيفلها
    0.90
    aarrggbb
    0.89
    DoubleQuotes
    0.88
    #+#
    0.86
    MarshalTo
    0.86
    Activations Density 0.282%

    No Known Activations