© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8890
    Prev
    Next
    INDEX
    Explanations

    the prefix "un" indicating negation or reversal of meaning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.76
    ModelSerializer
    -0.70
     Normdatei
    -0.69
    حياتها
    -0.66
     IFTT
    -0.64
    حياته
    -0.63
    MemoryWarning
    -0.62
     queſta
    -0.61
    ckså
    -0.59
    ſelben
    -0.58
    POSITIVE LOGITS
     un
    3.30
     Un
    2.23
    Un
    2.05
    un
    1.83
     UN
    1.48
     uns
    1.27
     unf
    1.24
     unt
    1.23
     Uns
    1.15
     unre
    1.14
    Activations Density 0.087%

    No Known Activations