© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 732
    Prev
    Next
    INDEX
    Explanations

    instances of directional language or movement-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     up
    -0.65
     tilbake
    -0.60
     forth
    -0.59
    ly
    -0.57
     upward
    -0.56
    forth
    -0.56
    able
    -0.56
     gawas
    -0.53
    着
    -0.52
    之为
    -0.52
    POSITIVE LOGITS
    GEBURTSDATUM
    0.71
     nicely
    0.68
    ioutil
    0.66
    IContainer
    0.66
    fjspx
    0.62
     للمعارف
    0.62
    resave
    0.61
    NameInMap
    0.61
     NSCoder
    0.61
    URLException
    0.61
    Activations Density 0.261%

    No Known Activations