© 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. 18-GEMMASCOPE-RES-16K
    11. 3498
    Prev
    Next
    INDEX
    Explanations

    technical language related to programming and system performance issues

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

    "Case" or "special values/scenarios"

    np_acts-logits-general · gemini-2.0-flash

    special cases and scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    basicConfig
    -0.62
    الإنجليزية
    -0.58
    Hentet
    -0.58
    ктан
    -0.57
     Waray
    -0.53
     ComVisible
    -0.52
    JspWriter
    -0.51
     relâche
    -0.49
     projects
    -0.49
     OrderedDict
    -0.48
    POSITIVE LOGITS
     scenarios
    1.16
     cases
    1.15
     scenario
    1.10
     situations
    1.05
     case
    1.04
     casos
    1.00
     Cases
    0.96
     Scenarios
    0.94
     Scenario
    0.93
    Cases
    0.92
    Activations Density 0.707%

    No Known Activations