© 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. 31-GEMMASCOPE-RES-16K
    11. 2601
    Prev
    Next
    INDEX
    Explanations

    connections between television stations and their news branding practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    broadcast television station call letters and time slots in local news programming contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    請繼續往下閱讀
    -0.47
     Taktlose
    -0.47
     Catawiki
    -0.44
    Reprodu
    -0.41
    Gön
    -0.39
     Svensk
    -0.38
    tone
    -0.37
    kloped
    -0.37
    ExecuteReader
    -0.37
     Budi
    -0.37
    POSITIVE LOGITS
     anchor
    0.63
     anchors
    0.62
     news
    0.61
     noticias
    0.58
     News
    0.58
     FOX
    0.55
     CBS
    0.54
    anchor
    0.54
     estación
    0.54
     meteoro
    0.53
    Activations Density 0.253%

    No Known Activations