© 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. 16021
    Prev
    Next
    INDEX
    Explanations

    elements of storytelling, particularly those highlighting characters' journeys and transformations

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

    Following a noun of people

    np_acts-logits-general · gemini-2.0-flash

    participant moving direction

    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
     disponibilités
    -0.61
     saja
    -0.54
     MotionEvent
    -0.54
    coming
    -0.51
    ücks
    -0.51
    estinal
    -0.47
     venuto
    -0.47
     Besøkt
    -0.47
     ViewPager
    -0.46
     CommonModule
    -0.46
    POSITIVE LOGITS
     onto
    1.03
     closer
    1.00
     forward
    0.86
     back
    0.86
     down
    0.86
     deeper
    0.85
     upstairs
    0.80
     away
    0.80
     ashore
    0.79
     home
    0.76
    Activations Density 0.229%

    No Known Activations