© 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. 38-GEMMASCOPE-RES-16K
    11. 7969
    Prev
    Next
    INDEX
    Explanations

    references to actors and films, particularly regarding their performances and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.63
    NewUrlParser
    -0.52
     engraçadas
    -0.51
    batore
    -0.50
     programu
    -0.50
    Tikang
    -0.49
    berdayakan
    -0.47
     alegre
    -0.46
    期刊论文
    -0.46
     Pembangunan
    -0.45
    POSITIVE LOGITS
     Academy
    0.60
     Cate
    0.58
    アカ
    0.56
     Kidman
    0.55
    Academy
    0.53
     Oscar
    0.53
    Cate
    0.52
     DiCaprio
    0.51
     Scorsese
    0.49
     academy
    0.48
    Activations Density 0.276%

    No Known Activations