© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9377
    Prev
    Next
    INDEX
    Explanations

    phrases related to transaction confirmations or order processing

    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
     kaarangay
    -0.61
    تفصیلات
    -0.60
    principalTable
    -0.60
     Reſ
    -0.59
    httphttps
    -0.58
     OnTrigger
    -0.57
     queſta
    -0.56
     FetchType
    -0.55
     raiſ
    -0.55
     Majefty
    -0.55
    POSITIVE LOGITS
     unique
    0.66
    randomUUID
    0.58
     uniquely
    0.56
     UNIQUE
    0.55
     unik
    0.54
     уника
    0.53
     ID
    0.53
    unique
    0.50
     Unique
    0.50
     UUID
    0.49
    Activations Density 0.555%

    No Known Activations