© 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. 24-GEMMASCOPE-RES-16K
    11. 16200
    Prev
    Next
    INDEX
    Explanations

    numerical values and their representations

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

    Chinese punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    Chinese game mechanics and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bed
    -0.45
    ECONDS
    -0.41
    hô
    -0.41
     half
    -0.39
     her
    -0.38
    惱
    -0.37
    沒想到
    -0.37
    alisco
    -0.37
    彼女の
    -0.36
     â
    -0.36
    POSITIVE LOGITS
    （
    0.54
    可
    0.52
    、
    0.52
    ，
    0.51
    等
    0.51
    和
    0.49
    ：
    0.46
    中
    0.45
    上
    0.44
    大
    0.44
    Activations Density 0.648%

    No Known Activations