© 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. 9245
    Prev
    Next
    INDEX
    Explanations

    elements related to targeted advertising and specifications of campaigns

    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
    でもあります
    -0.54
     inoltre
    -0.52
     ankaŭ
    -0.51
     malheureusement
    -0.51
     purtroppo
    -0.51
     außerdem
    -0.49
     myös
    -0.48
     navíc
    -0.48
     także
    -0.48
     anche
    -0.47
    POSITIVE LOGITS
     would
    0.72
    Would
    0.68
     Would
    0.67
     might
    0.65
     wouldnt
    0.64
     Wouldn
    0.63
    would
    0.63
    wouldn
    0.63
     uLocal
    0.62
     wouldn
    0.60
    Activations Density 0.583%

    No Known Activations