© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 582
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "purpose" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "purpose of" or "purposes of"

    np_acts-logits-general · gemini-2.0-flash

    purpose of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ckså
    -0.63
     Inscrivez
    -0.62
     argint
    -0.61
     CanadaChoose
    -0.59
     aéreo
    -0.58
    InjectAttribute
    -0.57
     inoxydable
    -0.57
    Autoritní
    -0.56
     sereia
    -0.56
     abogados
    -0.55
    POSITIVE LOGITS
     Purpose
    1.27
     purpose
    1.26
    Purpose
    1.16
     purposes
    1.10
    purpose
    1.09
     PURPOSE
    1.09
    PURPOSE
    1.01
     Purposes
    0.92
    purposes
    0.91
     purposeful
    0.79
    Activations Density 0.121%

    No Known Activations