© 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. 5-GEMMASCOPE-RES-16K
    11. 8743
    Prev
    Next
    INDEX
    Explanations

    phrases indicating acquisition or enhancement of knowledge or understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roberts
    -0.67
     I
    -0.63
     Stevenson
    -0.59
     Corcoran
    -0.59
     Brown
    -0.58
     pory
    -0.58
     Schroeder
    -0.58
     Wallace
    -0.56
     Morton
    -0.56
     Schröder
    -0.56
    POSITIVE LOGITS
     gain
    2.25
     Gain
    2.22
     GAIN
    2.21
    gain
    2.13
     gains
    2.08
     gained
    2.07
    Gain
    2.07
     Gains
    2.01
    gains
    1.79
    GAIN
    1.78
    Activations Density 0.044%

    No Known Activations