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-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8574
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or organizations in academic contexts

    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
     préc
    -0.46
     fermée
    -0.44
     dispozici
    -0.43
     obuv
    -0.43
     føl
    -0.43
     artificiales
    -0.42
     Eintritt
    -0.41
     CreateTagHelper
    -0.41
     eşofman
    -0.41
    harapkan
    -0.41
    POSITIVE LOGITS
     der
    0.95
     Der
    0.85
    Der
    0.85
    Dar
    0.81
     Dar
    0.81
     DER
    0.76
    DER
    0.74
     dar
    0.73
    der
    0.73
    Дер
    0.73
    Activations Density 1.591%

    No Known Activations