© 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. 18-GEMMASCOPE-RES-16K
    11. 8832
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding information verification and reliability in sources

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

    sources and credibility of information

    np_acts-logits-general · gemini-2.0-flash

    information source credibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    htaccess
    -0.48
    awar
    -0.47
    ArgumentParser
    -0.44
    jeb
    -0.44
    MockMvc
    -0.44
    complexContent
    -0.43
    Identyfik
    -0.43
    joi
    -0.42
     发表于
    -0.42
    aini
    -0.42
    POSITIVE LOGITS
     sources
    1.90
    sources
    1.65
     Sources
    1.64
     source
    1.61
    Sources
    1.56
     SOURCES
    1.49
     fuentes
    1.46
    source
    1.40
     fonti
    1.33
     fontes
    1.33
    Activations Density 0.349%

    No Known Activations