© 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. 13399
    Prev
    Next
    INDEX
    Explanations

    phrases related to parenting and child care

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

    preceding adverbs or verbs

    np_acts-logits-general · gemini-2.0-flash

    informal or critical language

    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
     אשר
    -0.75
    maktadır
    -0.70
     lecz
    -0.70
     attire
    -0.66
     již
    -0.63
     sculptured
    -0.62
    ,’’
    -0.59
     coloro
    -0.59
    mektedir
    -0.58
    ﹗
    -0.58
    POSITIVE LOGITS
     shitty
    1.26
     stuff
    1.20
     fucked
    1.17
     weirdly
    1.14
     kinda
    1.14
     iirc
    1.09
     fucking
    1.08
     sorta
    1.07
     whatnot
    1.06
     mierda
    1.05
    Activations Density 2.425%

    No Known Activations