© 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. 1-GEMMASCOPE-RES-16K
    11. 9467
    Prev
    Next
    INDEX
    Explanations

    mentions of "pocket" related to both physical items and metaphorical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.83
    setVerticalGroup
    -0.75
    onAttach
    -0.73
    AccessorTable
    -0.73
     Roskov
    -0.70
    ItemBackground
    -0.67
    TestingModule
    -0.66
     beginnetje
    -0.66
    JspWriter
    -0.64
    ValueGeneration
    -0.63
    POSITIVE LOGITS
    zer
    0.89
     lip
    0.83
    phazard
    0.76
    ZER
    0.74
     pocket
    0.73
    ches
    0.72
    compile
    0.72
     idle
    0.69
     compile
    0.68
     Lip
    0.68
    Activations Density 0.106%

    No Known Activations