© 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. 23-GEMMASCOPE-RES-16K
    6. 8779
    Prev
    Next
    INDEX
    Explanations

    details about smartphone charging and connectivity technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.68
    rxjs
    -0.66
     ffilmiau
    -0.60
    ValueStyle
    -0.57
     estekak
    -0.54
    WaitGroup
    -0.53
     GetEnumerator
    -0.53
    PointerException
    -0.53
    rehensible
    -0.53
    nski
    -0.52
    POSITIVE LOGITS
     charge
    2.75
     charging
    2.61
     Charge
    2.52
    Charge
    2.44
    charge
    2.43
     Charging
    2.29
    charging
    2.23
     charges
    2.20
     CHARGE
    2.19
     charged
    2.14
    Activations Density 0.156%

    No Known Activations