© 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-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9155
    Prev
    Next
    INDEX
    Explanations

    concepts related to moral and ethical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.56
    ombies
    -0.48
     gynhyrchwyd
    -0.48
    戬
    -0.45
    يميديا
    -0.45
    afone
    -0.44
     Dandy
    -0.44
     philipp
    -0.44
    曖昧さ回避
    -0.44
     colspan
    -0.44
    POSITIVE LOGITS
    RenderAtEndOf
    0.54
    fulness
    0.51
     elegance
    0.45
    ReusableCell
    0.42
     elegancia
    0.40
    reactstrap
    0.40
     clarity
    0.39
     regarding
    0.39
     Vergnügen
    0.39
     רבה
    0.38
    Activations Density 0.409%

    No Known Activations