© 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. 2-GEMMASCOPE-RES-16K
    11. 12640
    Prev
    Next
    INDEX
    Explanations

    comparative phrases emphasizing relational differences

    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
     queſta
    -0.64
     ſche
    -0.60
     preſent
    -0.59
    ſelf
    -0.58
     myſelf
    -0.56
     fubject
    -0.55
     pleaſure
    -0.54
     itſelf
    -0.54
     Reſ
    -0.54
    MigrationBuilder
    -0.54
    POSITIVE LOGITS
     than
    3.50
     THAN
    2.64
    than
    2.59
    Than
    2.58
     Than
    2.38
    THAN
    2.23
     niż
    2.22
     než
    1.73
     decât
    1.68
     än
    1.61
    Activations Density 0.107%

    No Known Activations