© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8533
    Prev
    Next
    INDEX
    Explanations

    terms related to observations and observation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     najm
    -0.37
    edizione
    -0.36
    aigu
    -0.34
    が
    -0.34
     Mangan
    -0.33
    Sight
    -0.32
     namorados
    -0.32
    mighty
    -0.32
     Sight
    -0.31
    appartement
    -0.31
    POSITIVE LOGITS
     observation
    2.72
     Observation
    2.50
     observe
    2.47
     observations
    2.38
     observing
    2.33
    Observation
    2.33
     OBSERV
    2.30
     observ
    2.28
    observation
    2.27
     Observations
    2.23
    Activations Density 0.111%

    No Known Activations