© 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. 27-GEMMASCOPE-RES-16K
    11. 9408
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.65
    mybatisplus
    -0.62
    andExpect
    -0.53
    Proced
    -0.53
    DebuggerStep
    -0.52
    Espèce
    -0.52
    PerformLayout
    -0.51
     CreateTagHelper
    -0.50
     Repo
    -0.50
     iNdEx
    -0.50
    POSITIVE LOGITS
     catalana
    0.44
     finanzas
    0.43
     chrétien
    0.40
     calientes
    0.35
    zerű
    0.35
     rzecz
    0.35
     oras
    0.35
     orgánica
    0.35
    ajinan
    0.34
     circulación
    0.34
    Activations Density 0.616%

    No Known Activations