© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 7419
    Prev
    Next
    INDEX
    Explanations

    terminology related to health and disease

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

    followed by suffixes like -ulate, -ments, -ures, -ases

    np_acts-logits-general · gemini-2.0-flash

    modulates, ferments, curler, insures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    észetes
    -0.68
    IUrlHelper
    -0.66
    rhosis
    -0.63
    visiae
    -0.62
    AndroidJUnit
    -0.62
    ynku
    -0.60
    脚注の使い方
    -0.60
    calyptic
    -0.59
    IEVE
    -0.58
    Personendaten
    -0.58
    POSITIVE LOGITS
     onPostExecute
    0.53
     doInBackground
    0.53
    BindingResult
    0.51
    reuung
    0.44
     nargin
    0.43
    Slf
    0.42
    PositiveButton
    0.41
     Pers
    0.40
    forName
    0.40
    égration
    0.39
    Activations Density 0.543%

    No Known Activations