© 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. 24-GEMMASCOPE-RES-16K
    6. 14231
    Prev
    Next
    INDEX
    Explanations

    references to mental states and cognitive processes

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

    followed by "mind"

    np_acts-logits-general · gemini-2.0-flash

    mind you, mind sets, mind management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annica
    -0.61
    mybatisplus
    -0.57
    Życiorys
    -0.57
    ⓘ
    -0.57
    AnchorStyles
    -0.51
    SerializeField
    -0.50
     metrów
    -0.50
    FontOfSize
    -0.50
    labelledby
    -0.50
    IBOutlet
    -0.50
    POSITIVE LOGITS
     wandering
    0.69
     wander
    0.67
     wanders
    0.64
    sets
    0.62
     bog
    0.61
    AccessorTable
    0.60
     wandered
    0.60
    🧠
    0.59
     palace
    0.57
    palace
    0.56
    Activations Density 0.109%

    No Known Activations