© 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. 15-GEMMASCOPE-RES-16K
    11. 1510
    Prev
    Next
    INDEX
    Explanations

    references to government entities or discussions regarding governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ★☆
    -0.46
    Parcours
    -0.44
     Mick
    -0.40
    处的
    -0.40
    roz
    -0.39
    başı
    -0.39
    AccessException
    -0.39
    Nick
    -0.38
    pleaños
    -0.38
    Roz
    -0.38
    POSITIVE LOGITS
     government
    1.16
     Government
    1.10
    government
    0.98
     govt
    0.96
     Govt
    0.96
     GOVERNMENT
    0.95
    Government
    0.94
    vernment
    0.93
     gobierno
    0.90
     Gouvernement
    0.88
    Activations Density 0.098%

    No Known Activations