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. 16-GEMMASCOPE-RES-16K
    6. 5282
    Prev
    Next
    INDEX
    Explanations

    terms related to thermodynamic properties and quantum systems

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

    "find that" or similar discoveries

    np_acts-logits-general · gemini-2.0-flash

    find conditions for dynamics

    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
     ویکی‌پدی
    -0.55
    ysacchar
    -0.52
     hini
    -0.50
    ätt
    -0.48
    acyl
    -0.45
    ByPrimaryKey
    -0.43
     pool
    -0.43
    face
    -0.43
     prisa
    -0.42
     ruhig
    -0.42
    POSITIVE LOGITS
    urlpatterns
    0.67
     Scenarios
    0.65
     scénario
    0.62
     Monfieur
    0.61
     uſ
    0.60
     scenarios
    0.59
     Inſ
    0.57
     OMITBAD
    0.57
     Conſ
    0.57
     LoggerFactory
    0.56
    Activations Density 1.612%

    No Known Activations