© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 10223
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or conditions in a procedural context

    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
    íté
    -0.25
     Hayward
    -0.25
     невозможно
    -0.25
     Rat
    -0.25
    kész
    -0.24
     sacré
    -0.24
     hå
    -0.23
     associations
    -0.23
     espoir
    -0.23
    也不能
    -0.22
    POSITIVE LOGITS
     unnecessary
    1.77
     inneces
    1.56
     need
    1.27
     needn
    1.23
    need
    1.23
     needless
    1.23
     superfluous
    1.19
     needed
    1.19
    needed
    1.18
     unnecessarily
    1.17
    Activations Density 0.703%

    No Known Activations