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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1769
    Prev
    Next
    INDEX
    Explanations

    concepts related to happiness and its development as a learned behavior

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

    ending in "able," "can," or "not"

    np_acts-logits-general · gemini-2.0-flash

    changeable, adjustable, removable

    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
    httphttps
    -0.52
     ainfi
    -0.47
    protoimpl
    -0.46
    ModelSerializer
    -0.45
    espejo
    -0.44
    Autoritní
    -0.42
    ientí
    -0.41
     يتيمه
    -0.40
    :✨
    -0.40
     anún
    -0.38
    POSITIVE LOGITS
     قابل
    1.05
     replaceable
    1.03
    可
    1.03
     changeable
    1.03
     removable
    1.01
     adjustable
    0.99
     controllable
    0.94
    changeable
    0.93
     movable
    0.93
    izable
    0.93
    Activations Density 0.657%

    No Known Activations