© 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. 8272
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional struggles and relationships

    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
     surla
    -0.73
    RenderAtEndOf
    -0.71
    adpleegd
    -0.59
    XmlRootElement
    -0.59
    NewReader
    -0.55
    marginHorizontal
    -0.55
     plen
    -0.55
     dyna
    -0.55
     Aggreg
    -0.54
    ፩
    -0.54
    POSITIVE LOGITS
     Gefühle
    0.62
     Wahrheit
    0.57
     honestly
    0.57
     perasaan
    0.57
    Honestly
    0.56
     knowing
    0.55
     truthfully
    0.53
     sedih
    0.53
     mendengar
    0.53
     sometimes
    0.51
    Activations Density 0.507%

    No Known Activations