© 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. 229
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration and decision-making within partnerships

    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
    ExtendWith
    -0.52
    VertexAttrib
    -0.48
    बस
    -0.46
    MessageTagHelper
    -0.46
    RTEE
    -0.45
    ViewFeatures
    -0.44
    tagHelperRunner
    -0.44
    Translatef
    -0.44
     poveznice
    -0.43
     đàn
    -0.43
    POSITIVE LOGITS
     choose
    2.98
     choosing
    2.92
     choice
    2.90
     chosen
    2.81
     chooses
    2.78
     chose
    2.73
     selecting
    2.70
    choose
    2.69
     selection
    2.67
     selected
    2.61
    Activations Density 1.118%

    No Known Activations