© 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. 33-GEMMASCOPE-RES-16K
    6. 10950
    Prev
    Next
    INDEX
    Explanations

    phrases related to anticipated future events and availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xrTableCell
    -0.32
     Einf
    -0.32
    Previous
    -0.30
     fö
    -0.30
    EndGlobalSection
    -0.29
     предыду
    -0.28
     Previous
    -0.28
    previous
    -0.28
    EO
    -0.27
    mybatisplus
    -0.27
    POSITIVE LOGITS
     soon
    3.69
    Soon
    3.09
    soon
    3.09
     Soon
    3.03
     SOON
    2.73
     bientôt
    2.39
     snart
    2.31
     foon
    2.22
     shortly
    2.05
    ientôt
    1.80
    Activations Density 0.627%

    No Known Activations