© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 10959
    Prev
    Next
    INDEX
    Explanations

    references to government entities and their actions or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ★☆
    -0.57
    drill
    -0.52
    roz
    -0.48
     drill
    -0.46
    scan
    -0.46
    Roz
    -0.45
     Miles
    -0.45
     Milán
    -0.45
    Needle
    -0.45
    Nick
    -0.45
    POSITIVE LOGITS
     government
    0.94
     Government
    0.91
    government
    0.79
    vernment
    0.79
    Government
    0.77
     GOVERNMENT
    0.76
     gobierno
    0.75
     Gouvernement
    0.75
     Govt
    0.73
     govt
    0.71
    Activations Density 0.099%

    No Known Activations