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-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4496
    Prev
    Next
    INDEX
    Explanations

    references to legal rules and procedures in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.58
    ftagPool
    -0.54
     Soria
    -0.52
     queſto
    -0.52
    esty
    -0.50
    ๣
    -0.49
    fromnode
    -0.49
    下
    -0.49
    fuhr
    -0.48
    enska
    -0.48
    POSITIVE LOGITS
    ########.
    0.45
     raiſ
    0.40
     mourut
    0.39
    Хьажоргаш
    0.38
     anún
    0.36
     quelcon
    0.35
     Administrativna
    0.35
     avoient
    0.34
     faſt
    0.34
     devenus
    0.34
    Activations Density 3.139%

    No Known Activations