© 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. 12694
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings and concerns regarding interpersonal relationships

    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
    ///</
    -0.82
    יצד
    -0.69
     CreateTagHelper
    -0.64
     terrific
    -0.64
    Amicalement
    -0.63
     météo
    -0.62
     épouse
    -0.61
    sightly
    -0.61
     figliu
    -0.58
     malady
    -0.58
    POSITIVE LOGITS
     idk
    0.99
    idk
    0.95
     Idk
    0.92
    Idk
    0.87
    localctx
    0.86
     hella
    0.85
     tryna
    0.74
     asf
    0.71
     irl
    0.70
     fuckin
    0.70
    Activations Density 0.294%

    No Known Activations