© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 6866
    Prev
    Next
    INDEX
    Explanations

    specific temperature measurements expressed in degrees Celsius and Fahrenheit

    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
     AssemblyTitle
    -0.74
     يتيمه
    -0.71
     resourceCulture
    -0.70
    mybatisplus
    -0.69
    ModelSerializer
    -0.66
    rungsseite
    -0.64
    principalColumn
    -0.57
     فريبيس
    -0.57
    पया
    -0.57
    __(/*!
    -0.56
    POSITIVE LOGITS
     Celsius
    0.96
     Fahrenheit
    0.86
    Celsius
    0.83
    Fahren
    0.69
     Fahren
    0.69
     celsius
    0.68
     Centi
    0.67
     fahren
    0.66
    C
    0.64
     centi
    0.63
    Activations Density 0.184%

    No Known Activations