© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 3092
    Prev
    Next
    INDEX
    Explanations

    references to phases in a process or study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GRAFÍA
    -0.91
    ]--;
    -0.90
    ]='\
    -0.84
     "'");
    -0.76
     Müll
    -0.75
    ]]);
    -0.73
    ')")
    -0.70
    ]))
    -0.70
     Mercurio
    -0.70
    '))
    -0.69
    POSITIVE LOGITS
     STAGE
    1.38
    Stage
    1.35
     PHASE
    1.34
     Stage
    1.33
     phase
    1.31
     Phase
    1.28
    PHASE
    1.27
    phase
    1.26
    STAGE
    1.25
    stage
    1.23
    Activations Density 0.048%

    No Known Activations