© 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. 27-GEMMASCOPE-RES-16K
    11. 9904
    Prev
    Next
    INDEX
    Explanations

    terms related to privacy and private ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __["
    -0.45
    cephala
    -0.44
    Represent
    -0.42
    jarse
    -0.42
     Represent
    -0.41
     Poc
    -0.38
     cref
    -0.38
     tetto
    -0.38
     beziehen
    -0.37
    resented
    -0.36
    POSITIVE LOGITS
     Pri
    0.76
    Pri
    0.75
    pri
    0.65
     pri
    0.64
     Priory
    0.59
     privatization
    0.59
     Italijanski
    0.57
     Biôgrafia
    0.57
     privé
    0.56
     betweenstory
    0.55
    Activations Density 0.291%

    No Known Activations