© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 12736
    Prev
    Next
    INDEX
    Explanations

    references to numerical quantities or comparisons indicating "more" or "less"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    printStackTrace
    -0.39
    SPATH
    -0.38
    ("'"
    -0.38
    ########.
    -0.37
    marginHorizontal
    -0.36
    Děkuji
    -0.34
    liothèque
    -0.34
    guigu
    -0.34
     чуть
    -0.33
     känna
    -0.33
    POSITIVE LOGITS
     OFDb
    0.66
     itſelf
    0.64
     이상
    0.59
    ſelf
    0.56
    hyrchwyd
    0.55
     leaſt
    0.53
     Wikimedijinoj
    0.52
    ſelves
    0.52
     themſelves
    0.51
     raiſ
    0.51
    Activations Density 0.292%

    No Known Activations