© 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. 14-GEMMASCOPE-RES-16K
    11. 8803
    Prev
    Next
    INDEX
    Explanations

    code structures related to data serialization and deserialization using JSON

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     محفوظة
    -0.46
    求
    -0.40
     lovely
    -0.38
     touched
    -0.38
     beautiful
    -0.38
     verbal
    -0.38
    ècie
    -0.37
     sleep
    -0.37
     visual
    -0.36
     gorgeous
    -0.36
    POSITIVE LOGITS
    ViewImports
    0.68
    InjectMocks
    0.63
    RenderAtEndOf
    0.62
     getService
    0.62
     informée
    0.60
    StoryboardSegue
    0.59
    GRANTED
    0.58
     TestBed
    0.57
     infrastructure
    0.57
    tagHelperRunner
    0.57
    Activations Density 0.331%

    No Known Activations