© 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. 3-GEMMASCOPE-RES-16K
    11. 5810
    Prev
    Next
    INDEX
    Explanations

    mentions of ions and ion-related processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ricul
    -0.76
    cdnjs
    -0.71
     indiri
    -0.67
    xbb
    -0.66
    HandlerContext
    -0.64
    __*/
    -0.63
    adaptiveStyles
    -0.60
     esimer
    -0.59
    avras
    -0.59
     palk
    -0.59
    POSITIVE LOGITS
     ion
    2.93
    ion
    2.81
     Ion
    2.64
     ions
    2.49
    Ion
    2.49
    ION
    2.41
     ION
    2.31
    ions
    2.06
    ionic
    1.71
     ionic
    1.52
    Activations Density 0.126%

    No Known Activations