© 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. 18-GEMMASCOPE-RES-16K
    11. 2940
    Prev
    Next
    INDEX
    Explanations

    specific mathematical notation and structured data format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Letters after a capitalized letter (A, B, or C)

    np_acts-logits-general · gemini-2.0-flash

    third option. third group. third arm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BEAM
    -0.53
    queryInterface
    -0.49
    medriver
    -0.49
     Wide
    -0.48
     Bask
    -0.48
    ANDRO
    -0.48
    ]--;
    -0.47
    ագրություններ
    -0.47
     MATER
    -0.47
    mares
    -0.46
    POSITIVE LOGITS
     third
    1.11
    third
    1.05
     terceiro
    0.91
    第三
    0.90
    Third
    0.89
    THIRD
    0.89
     Thirdly
    0.87
     dritte
    0.83
     terceira
    0.83
     Third
    0.83
    Activations Density 0.485%

    No Known Activations