© 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. 0-GEMMASCOPE-RES-16K
    11. 7456
    Prev
    Next
    INDEX
    Explanations

    technical terms and conditions related to user accounts and privacy policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cim
    -1.97
     corne
    -1.96
     fec
    -1.96
     inci
    -1.95
     sof
    -1.95
     pizz
    -1.94
     sere
    -1.94
     raf
    -1.94
     blin
    -1.93
     arca
    -1.93
    POSITIVE LOGITS
     zijne
    4.19
     mijne
    4.19
     desmotivaciones
    3.56
     Económica
    3.48
     istrinya
    3.41
     miniaturka
    3.39
     extranjera
    3.31
     kysy
    3.30
     zelve
    3.27
     esclavos
    3.27
    Activations Density 2.889%

    No Known Activations