© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8239
    Prev
    Next
    INDEX
    Explanations

    references to "high" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.57
    lause
    -0.48
    AnimationsModule
    -0.45
    ulism
    -0.45
    cellation
    -0.45
    opsis
    -0.44
    apter
    -0.42
    egis
    -0.41
    tula
    -0.40
    ndel
    -0.40
    POSITIVE LOGITS
     High
    3.97
    High
    3.77
     high
    2.98
     HIGH
    2.94
    high
    2.92
    HIGH
    2.66
    高
    2.09
    Высо
    1.99
     Высо
    1.97
    的高
    1.96
    Activations Density 0.126%

    No Known Activations