© 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. 11-GEMMASCOPE-RES-16K
    6. 13391
    Prev
    Next
    INDEX
    Explanations

    phrases related to bug tracking and software quality assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -0.65
     متعلقه
    -0.62
    SourceChecksum
    -0.60
     GetEnumerator
    -0.59
    exitRule
    -0.58
     défend
    -0.58
    Datuak
    -0.57
     Garantie
    -0.56
    TypedDataSet
    -0.56
     sacrificed
    -0.55
    POSITIVE LOGITS
    міна
    0.56
     reporting
    0.54
     marking
    0.49
     mark
    0.48
     log
    0.48
    '])->
    0.47
     Log
    0.46
    ERVER
    0.46
     son
    0.44
     recorded
    0.43
    Activations Density 0.315%

    No Known Activations