Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2125
    Prev
    Next
    INDEX
    Explanations

    equipment and items used for practical purposes

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

    items related to tent and camping equipment

    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
    liferay
    -0.53
    InputTagHelper
    -0.52
     Wirt
    -0.48
    FontOfSize
    -0.47
    Kaynakça
    -0.46
    regon
    -0.45
    rą
    -0.44
     Dishwasher
    -0.44
    Dishwasher
    -0.44
    StackSize
    -0.43
    POSITIVE LOGITS
     tarp
    1.15
     tent
    1.01
     fabric
    1.01
     canvas
    0.99
     curtains
    0.99
     canopy
    0.96
     cloth
    0.96
     Curtains
    0.92
     tents
    0.92
     awning
    0.91
    Activations Density 0.316%

    No Known Activations