© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15176
    Prev
    Next
    INDEX
    Explanations

    phrases expressing indifference or lack of concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "care" or "matter"

    np_acts-logits-general · gemini-2.0-flash

    expressing indifference or care

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.56
     CreateTagHelper
    -0.55
    jooq
    -0.48
    TestingModule
    -0.48
     aéreas
    -0.48
    ArgsConstructor
    -0.47
    OCCURRED
    -0.45
    fohlen
    -0.44
     BufferedWriter
    -0.44
     metav
    -0.43
    POSITIVE LOGITS
     cares
    1.18
     cared
    1.15
     care
    1.06
     peduli
    1.03
     mattered
    0.99
     matter
    0.92
     concern
    0.91
     whether
    0.91
     caring
    0.89
     Care
    0.87
    Activations Density 0.144%

    No Known Activations