© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4240
    Prev
    Next
    INDEX
    Explanations

    references to mental and emotional states

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

    "soul" or "mind."

    np_acts-logits-general · gemini-2.0-flash

    mind and soul

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.67
    tvguidetime
    -0.57
    #+#
    -0.56
    wapV
    -0.56
     BrowserModule
    -0.56
     nahilalakip
    -0.56
     كومونز
    -0.55
    Vidite
    -0.55
    PostInfinity
    -0.54
     Италијани
    -0.54
    POSITIVE LOGITS
    Mind
    0.60
     Mind
    0.60
    mind
    0.55
     mind
    0.52
     MIND
    0.49
    Soul
    0.47
     Soul
    0.42
    */].
    0.41
     spent
    0.40
    loss
    0.40
    Activations Density 0.136%

    No Known Activations