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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15159
    Prev
    Next
    INDEX
    Explanations

    cars and their specifications, particularly focusing on performance and design attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mergeFrom
    -0.63
    AnchorStyles
    -0.55
    saida
    -0.53
    WithDefault
    -0.51
    álás
    -0.50
     PANEL
    -0.49
    Demografie
    -0.49
     الحره
    -0.49
     Panel
    -0.49
    cektir
    -0.49
    POSITIVE LOGITS
     racing
    0.74
     motorsport
    0.71
     Bugatti
    0.67
    apimachinery
    0.61
     esternos
    0.61
     springfox
    0.60
     Pors
    0.58
    hoeddwyd
    0.58
     thrills
    0.58
    orghini
    0.58
    Activations Density 0.158%

    No Known Activations