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. 23-GEMMASCOPE-RES-16K
    6. 2381
    Prev
    Next
    INDEX
    Explanations

    travel-related actions, especially related to fleeing or moving towards something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.71
     يتيمه
    -0.69
    Билгалдахарш
    -0.68
    KommentareTeilen
    -0.67
    AddTagHelper
    -0.65
    SourceChecksum
    -0.65
     Lightboxes
    -0.65
     informée
    -0.64
     Taktlose
    -0.64
    VYMaps
    -0.63
    POSITIVE LOGITS
     away
    0.35
     separate
    0.35
     yoksa
    0.30
     göm
    0.28
     dietro
    0.27
    MetaObject
    0.27
     gitti
    0.27
     Geschle
    0.27
     terpisah
    0.27
    zoeken
    0.26
    Activations Density 0.298%

    No Known Activations