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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 4168
    Prev
    Next
    INDEX
    Explanations

    adjectives describing qualities or characteristics of objects

    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
     calendriers
    -0.63
    numerusform
    -0.52
     simplicity
    -0.51
     seriousness
    -0.50
    //}
    
    -0.49
    <bos>
    -0.48
     reliability
    -0.47
    cachor
    -0.47
     незавершена
    -0.47
    realloc
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.66
     course
    0.63
     absorbent
    0.61
     firm
    0.61
    course
    0.59
    pli
    0.58
    writeFieldEnd
    0.57
    BrowserModule
    0.55
     BrowserModule
    0.54
    Course
    0.53
    Activations Density 0.246%

    No Known Activations