© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 16061
    Prev
    Next
    INDEX
    Explanations

    references to feelings of awakening or realization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defStyle
    -0.60
     onCancelled
    -0.58
     riserv
    -0.56
    OGND
    -0.53
     Ei
    -0.53
    Resident
    -0.52
    beros
    -0.51
     Esses
    -0.51
     symptomatic
    -0.50
     weakens
    -0.50
    POSITIVE LOGITS
    AnchorStyles
    0.70
    MemoryWarning
    0.69
    HtmlAttribute
    0.57
    UnknownFieldSet
    0.54
    StoreMessageInfo
    0.53
    TagHelper
    0.52
    ImageContext
    0.51
    anwal
    0.50
    hæng
    0.49
     ExecuteAsync
    0.49
    Activations Density 0.140%

    No Known Activations