© 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. 33-GEMMASCOPE-RES-16K
    11. 645
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific and systematic structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quidem
    -0.49
    లాలు
    -0.48
    日閲覧
    -0.47
    談社
    -0.44
    GTCX
    -0.43
    _));
    -0.42
     antaranya
    -0.42
    🇶
    -0.40
     zufolge
    -0.38
     Wikimedijinoj
    -0.37
    POSITIVE LOGITS
     characteristic
    1.21
    characteristic
    1.16
     typical
    1.07
     seen
    0.98
     prevalent
    0.98
     found
    0.94
    typical
    0.91
     Characteristic
    0.91
     característica
    0.91
     характер
    0.90
    Activations Density 0.957%

    No Known Activations