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. 11-GEMMASCOPE-RES-16K
    6. 14264
    Prev
    Next
    INDEX
    Explanations

    words and concepts related to electronic components, particularly LEDs and DC motors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     */}
    -0.79
    índ
    -0.71
     same
    -0.70
     STC
    -0.68
     cual
    -0.67
    lands
    -0.65
    `{.
    -0.65
    ative
    -0.64
     hab
    -0.64
     SWT
    -0.64
    POSITIVE LOGITS
    tencent
    0.89
    ristmas
    0.87
     mums
    0.85
     McPherson
    0.83
     mohair
    0.81
    rrggbb
    0.81
    GraphicsUnit
    0.80
    cherichia
    0.80
    SpringRunner
    0.79
     Etr
    0.78
    Activations Density 0.139%

    No Known Activations