© 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. 18-GEMMASCOPE-RES-16K
    6. 7089
    Prev
    Next
    INDEX
    Explanations

    phrases related to political norms and the importance of public trust

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

    Follows a form of the verb "to be"

    np_acts-logits-general · gemini-2.0-flash

    forms of "to be" followed by adjectives

    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
    ň
    -0.46
    名詞
    -0.45
     ["",
    -0.44
     Opiniones
    -0.41
    ボリューム
    -0.40
    nolog
    -0.39
     peristiwa
    -0.39
    versch
    -0.39
     reseñas
    -0.39
    šte
    -0.38
    POSITIVE LOGITS
    complexType
    0.81
    principalColumn
    0.80
    BibitemShut
    0.76
     itſelf
    0.74
     AssemblyTitle
    0.71
     trait
    0.70
    OOTDTY
    0.70
    KURZBESCHREIBUNG
    0.69
    AddHtmlAttribute
    0.69
     Characteristic
    0.69
    Activations Density 0.351%

    No Known Activations