© 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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 4844
    Prev
    Next
    INDEX
    Explanations

    instances of conjunctions and transitions in the text

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

    "even" and its translations

    np_acts-logits-general · gemini-2.0-flash

    even then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    兼
    -0.47
    oprop
    -0.43
     兼
    -0.41
    domésticos
    -0.41
    vin
    -0.40
    beginTransaction
    -0.40
    пре
    -0.39
    sets
    -0.39
    momix
    -0.38
    xda
    -0.38
    POSITIVE LOGITS
     even
    1.51
    even
    1.33
     EVEN
    1.22
    Even
    1.21
     Even
    1.19
     sogar
    1.08
    EVEN
    1.06
     навіть
    1.06
     persino
    1.01
     даже
    0.98
    Activations Density 0.302%

    No Known Activations