© 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. 22-GEMMASCOPE-RES-16K
    11. 16296
    Prev
    Next
    INDEX
    Explanations

    concepts related to comparison and evaluation in various contexts

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

    "... purposes", "purposes", or "purpose"

    np_acts-logits-general · gemini-2.0-flash

    explaining purposes or reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -2.00
    for
    -1.38
     untuk
    -1.18
     для
    -1.13
     برای
    -1.06
     voor
    -1.03
     für
    -1.00
     pentru
    -0.95
     για
    -0.95
     för
    -0.92
    POSITIVE LOGITS
     purposes
    2.07
    purposes
    1.68
     Purposes
    1.59
     sake
    1.48
     purpose
    1.41
    purpose
    1.13
    Purpose
    1.12
     Purpose
    1.10
     Sake
    1.08
     reasons
    1.06
    Activations Density 0.639%

    No Known Activations