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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 7494
    Prev
    Next
    INDEX
    Explanations

    expressions and concepts related to self-perception and personal identity in relation to professional and emotional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propTypes
    -0.70
    sslich
    -0.65
     merve
    -0.65
     valide
    -0.64
    ⓧ
    -0.63
     côtes
    -0.62
     civile
    -0.62
     Halen
    -0.60
     religieuses
    -0.59
     exemplaire
    -0.59
    POSITIVE LOGITS
     vibe
    1.00
     atmosphere
    0.99
     feeling
    0.92
     ambiance
    0.87
     ambience
    0.83
     vibes
    0.83
     impression
    0.82
     atmos
    0.82
    氛
    0.81
    feeling
    0.80
    Activations Density 0.178%

    No Known Activations