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

    Neuronpedia

    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. 9020
    Prev
    Next
    INDEX
    Explanations

    requests for explanations or assistance

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

    Following verbs of communication/offering

    np_acts-logits-general · gemini-2.0-flash

    information given to me

    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
    Rhestr
    -0.65
    ArgsConstructor
    -0.64
    HostException
    -0.61
    yntaxException
    -0.60
    ]<<"
    -0.57
    èdia
    -0.56
    peza
    -0.52
    URLException
    -0.51
     microfilm
    -0.50
     Rosary
    -0.49
    POSITIVE LOGITS
     me
    1.58
     us
    1.50
     нам
    1.30
     meille
    1.22
     мне
    1.01
     вам
    0.90
     you
    0.85
     мені
    0.84
     لنا
    0.84
    me
    0.83
    Activations Density 0.478%

    No Known Activations