© 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. 2-GEMMASCOPE-RES-16K
    11. 8977
    Prev
    Next
    INDEX
    Explanations

    references to the number two in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.69
     propOrder
    -0.58
     actionMode
    -0.49
    MessageTagHelper
    -0.46
    migrationBuilder
    -0.44
     TextAppearance
    -0.44
     HasFactory
    -0.44
    newtheorem
    -0.41
    disposing
    -0.40
     StringField
    -0.40
    POSITIVE LOGITS
     beiden
    1.15
     दोनों
    0.88
     båda
    0.86
     Beide
    0.81
     both
    0.81
    Ambos
    0.80
     beide
    0.80
     ambos
    0.78
     keduanya
    0.77
     entrambi
    0.77
    Activations Density 0.175%

    No Known Activations