© 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. 3-GEMMASCOPE-RES-16K
    11. 13044
    Prev
    Next
    INDEX
    Explanations

    variations of the word "obtain."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setTime
    -0.72
     Trix
    -0.70
     grace
    -0.64
    affaires
    -0.63
     pilar
    -0.61
     act
    -0.60
    UserDto
    -0.60
     play
    -0.60
    setName
    -0.59
    yesha
    -0.59
    POSITIVE LOGITS
     obtained
    2.65
     obtain
    2.55
     obtains
    2.49
    obtained
    2.46
     Obtain
    2.40
    Obtain
    2.37
     Obtained
    2.35
     obtaining
    2.34
     Obtaining
    2.29
    obtain
    2.28
    Activations Density 0.076%

    No Known Activations