© 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. 20-GEMMASCOPE-RES-16K
    6. 2259
    Prev
    Next
    INDEX
    Explanations

    terms related to increasing trends and challenges within society

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

    phrases about growing trends or increasing importance in various contexts (population, development, community, etc.).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conceptual
    -0.43
    arakat
    -0.43
    rzez
    -0.43
     lenker
    -0.42
    MockMvc
    -0.41
     Rechten
    -0.41
    marvin
    -0.41
    ❦
    -0.40
    amatkan
    -0.40
    rinfo
    -0.40
    POSITIVE LOGITS
     increasingly
    0.84
    越来越
    0.73
    越來越
    0.72
    越来越多
    0.69
     zuneh
    0.64
     crescente
    0.64
     Increasing
    0.63
     creciente
    0.63
    Increasing
    0.62
    越來
    0.62
    Activations Density 0.146%

    No Known Activations