© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 1552
    Prev
    Next
    INDEX
    Explanations

    terms related to advancement or progress in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itename
    -0.68
    wußt
    -0.66
    mability
    -0.63
     Kraus
    -0.59
     kasarigan
    -0.59
    ειτουργ
    -0.58
     électron
    -0.58
    odils
    -0.57
    nesia
    -0.56
    imageshack
    -0.56
    POSITIVE LOGITS
     Advance
    1.12
    Advance
    1.08
     ADVANCE
    1.01
     advance
    1.01
    Adv
    0.97
     Advanced
    0.89
    advanced
    0.87
    advance
    0.87
    Advanced
    0.86
     advanced
    0.85
    Activations Density 0.114%

    No Known Activations