© 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. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 109244
    Prev
    Next
    INDEX
    Explanations

    terms related to apprehension and capture, particularly in the context of law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apprehended
    -1.40
     apprehension
    -1.29
     apprehend
    -1.25
     apprehensions
    -1.01
     appre
    -0.91
     apprehen
    -0.89
     apprehensive
    -0.79
    rehension
    -0.67
     appré
    -0.55
    hending
    -0.54
    POSITIVE LOGITS
    IsPostBack
    0.55
    jsxFileName
    0.53
     Dro
    0.41
    JoinColumn
    0.39
     Di
    0.39
    bnf
    0.39
     leak
    0.38
     Beck
    0.37
    nanoTime
    0.37
    TestTools
    0.37
    Activations Density 0.001%

    No Known Activations