© 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. 25-GEMMASCOPE-RES-16K
    6. 12233
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical conditions or circumstances related to an event or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.54
    meanor
    -0.50
    Sung
    -0.50
    EnableWeb
    -0.50
    
    -0.48
     Sung
    -0.46
    μως
    -0.46
    Races
    -0.45
    +#+
    -0.45
    writeValue
    -0.45
    POSITIVE LOGITS
     bed
    1.62
     mattress
    1.38
     beds
    1.32
     Bed
    1.20
     bedding
    1.14
     mattresses
    1.14
     Mattress
    1.14
    Bed
    1.13
     Beds
    1.10
    bed
    1.09
    Activations Density 0.183%

    No Known Activations