© 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. 23-GEMMASCOPE-RES-16K
    11. 9071
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate purpose or intent, typically structured as "in order to."

    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
     desn
    -0.48
    BibitemShut
    -0.47
     Responsibility
    -0.43
    Responsibility
    -0.43
    esub
    -0.42
    tellations
    -0.42
     contemp
    -0.42
     Hemis
    -0.41
    もしろ
    -0.41
     kaynağından
    -0.41
    POSITIVE LOGITS
     כדי
    0.65
     أجل
    0.60
     щоб
    0.60
     чтобы
    0.59
    Notae
    0.59
     to
    0.56
     جهت
    0.54
     afin
    0.52
    Източници
    0.52
    OGND
    0.51
    Activations Density 0.134%

    No Known Activations