© 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. 7651
    Prev
    Next
    INDEX
    Explanations

    numbers or numerical data

    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
     terça
    -0.55
     bezeichneter
    -0.55
    urlpatterns
    -0.53
     StatefulWidget
    -0.52
     nine
    -0.52
    AlterField
    -0.51
    Rhestr
    -0.51
     quinze
    -0.51
    DebuggerNonUser
    -0.50
     gynhyrchwyd
    -0.48
    POSITIVE LOGITS
    4
    2.20
     four
    1.86
     Four
    1.81
     fourth
    1.69
     Fourth
    1.67
    four
    1.67
    四
    1.61
    4
    1.59
    Four
    1.59
     FOUR
    1.58
    Activations Density 3.700%

    No Known Activations