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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7925
    Prev
    Next
    INDEX
    Explanations

    dialogues and character interactions in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URLException
    -0.71
     препратки
    -0.65
     AssemblyTitle
    -0.60
    ſelf
    -0.59
    السكان
    -0.57
    SharedCtor
    -0.57
     AppCompatTheme
    -0.56
    SerializedSize
    -0.56
     ffilmiau
    -0.53
     للمعارف
    -0.53
    POSITIVE LOGITS
     счита
    0.32
     prime
    0.32
     démocr
    0.31
     TMPro
    0.29
     INTERFACE
    0.29
    adomo
    0.27
     pozor
    0.27
     Distrito
    0.27
     microp
    0.27
     tratto
    0.26
    Activations Density 0.036%

    No Known Activations